From 75c4511e6b81ae8fb0dbd932043e8eb35cd09f72 Mon Sep 17 00:00:00 2001
From: zhaohu xing <920232796@qq.com>
Date: Tue, 29 Nov 2022 10:28:41 +0800
Subject: add AltDiffusion to webui

Signed-off-by: zhaohu xing <920232796@qq.com>
---
 modules/shared.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'modules/shared.py')

diff --git a/modules/shared.py b/modules/shared.py
index c93ae2a3..9941d2f4 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -21,7 +21,7 @@ from modules.paths import models_path, script_path, sd_path
 sd_model_file = os.path.join(script_path, 'model.ckpt')
 default_sd_model_file = sd_model_file
 parser = argparse.ArgumentParser()
-parser.add_argument("--config", type=str, default=os.path.join(sd_path, "configs/stable-diffusion/v1-inference.yaml"), help="path to config which constructs model",)
+parser.add_argument("--config", type=str, default="configs/altdiffusion/ad-inference.yaml", help="path to config which constructs model",)
 parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
 parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
 parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
@@ -106,6 +106,10 @@ restricted_opts = {
     "outdir_txt2img_grids",
     "outdir_save",
 }
+from omegaconf import OmegaConf
+config = OmegaConf.load(f"{cmd_opts.config}")
+# XLMR-Large
+text_model_name = config.model.params.cond_stage_config.params.name
 
 cmd_opts.disable_extension_access = (cmd_opts.share or cmd_opts.listen or cmd_opts.server_name) and not cmd_opts.enable_insecure_extension_access
 
-- 
cgit v1.2.3


From 9c86fb8cace6d8ac0843e0ddad0ba5ae7f3148c9 Mon Sep 17 00:00:00 2001
From: zhaohu xing <920232796@qq.com>
Date: Fri, 2 Dec 2022 16:08:46 +0800
Subject: fix bug

Signed-off-by: zhaohu xing <920232796@qq.com>
---
 modules/shared.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'modules/shared.py')

diff --git a/modules/shared.py b/modules/shared.py
index 1408dee3..ac7678c3 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -111,7 +111,11 @@ restricted_opts = {
 from omegaconf import OmegaConf
 config = OmegaConf.load(f"{cmd_opts.config}")
 # XLMR-Large
-text_model_name = config.model.params.cond_stage_config.params.name
+try:
+    text_model_name = config.model.params.cond_stage_config.params.name
+
+except :
+    text_model_name = "stable_diffusion"
 
 cmd_opts.disable_extension_access = (cmd_opts.share or cmd_opts.listen or cmd_opts.server_name) and not cmd_opts.enable_insecure_extension_access
 
-- 
cgit v1.2.3


From 965fc5ac5a6ccdf38342e21c97183011a04e799e Mon Sep 17 00:00:00 2001
From: zhaohu xing <920232796@qq.com>
Date: Tue, 6 Dec 2022 16:15:15 +0800
Subject: delete a file

Signed-off-by: zhaohu xing <920232796@qq.com>
---
 .DS_Store         | Bin 6148 -> 0 bytes
 modules/shared.py |   2 +-
 2 files changed, 1 insertion(+), 1 deletion(-)
 delete mode 100644 .DS_Store

(limited to 'modules/shared.py')

diff --git a/.DS_Store b/.DS_Store
deleted file mode 100644
index 5008ddfc..00000000
Binary files a/.DS_Store and /dev/null differ
diff --git a/modules/shared.py b/modules/shared.py
index 522c56c1..8419b531 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -22,7 +22,7 @@ demo = None
 sd_model_file = os.path.join(script_path, 'model.ckpt')
 default_sd_model_file = sd_model_file
 parser = argparse.ArgumentParser()
-parser.add_argument("--config", type=str, default="configs/altdiffusion/ad-inference.yaml", help="path to config which constructs model",)
+parser.add_argument("--config", type=str, default=os.path.join(script_path, "v1-inference.yaml"), help="path to config which constructs model",)
 parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
 parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
 parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
-- 
cgit v1.2.3


From 893933e05ad267778111b4fad6d1ecb80937afdf Mon Sep 17 00:00:00 2001
From: hitomi <huahuohe@foxmail.com>
Date: Sun, 25 Dec 2022 20:49:25 +0800
Subject: Add memory cache for VAE weights

---
 modules/sd_vae.py | 31 +++++++++++++++++++++++++------
 modules/shared.py |  1 +
 2 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'modules/shared.py')

diff --git a/modules/sd_vae.py b/modules/sd_vae.py
index 3856418e..ac71d62d 100644
--- a/modules/sd_vae.py
+++ b/modules/sd_vae.py
@@ -1,5 +1,6 @@
 import torch
 import os
+import collections
 from collections import namedtuple
 from modules import shared, devices, script_callbacks
 from modules.paths import models_path
@@ -30,6 +31,7 @@ base_vae = None
 loaded_vae_file = None
 checkpoint_info = None
 
+checkpoints_loaded = collections.OrderedDict()
 
 def get_base_vae(model):
     if base_vae is not None and checkpoint_info == model.sd_checkpoint_info and model:
@@ -149,13 +151,30 @@ def load_vae(model, vae_file=None):
     global first_load, vae_dict, vae_list, loaded_vae_file
     # save_settings = False
 
+    cache_enabled = shared.opts.sd_vae_checkpoint_cache > 0
+
     if vae_file:
-        assert os.path.isfile(vae_file), f"VAE file doesn't exist: {vae_file}"
-        print(f"Loading VAE weights from: {vae_file}")
-        store_base_vae(model)
-        vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)
-        vae_dict_1 = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}
-        _load_vae_dict(model, vae_dict_1)
+        if cache_enabled and vae_file in checkpoints_loaded:
+            # use vae checkpoint cache
+            print(f"Loading VAE weights [{get_filename(vae_file)}] from cache")
+            store_base_vae(model)
+            _load_vae_dict(model, checkpoints_loaded[vae_file])
+        else:
+            assert os.path.isfile(vae_file), f"VAE file doesn't exist: {vae_file}"
+            print(f"Loading VAE weights from: {vae_file}")
+            store_base_vae(model)
+            vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)
+            vae_dict_1 = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}
+            _load_vae_dict(model, vae_dict_1)
+
+            if cache_enabled:
+                # cache newly loaded vae
+                checkpoints_loaded[vae_file] = vae_dict_1.copy()
+
+        # clean up cache if limit is reached
+        if cache_enabled:
+            while len(checkpoints_loaded) > shared.opts.sd_vae_checkpoint_cache + 1: # we need to count the current model
+                checkpoints_loaded.popitem(last=False)  # LRU
 
         # If vae used is not in dict, update it
         # It will be removed on refresh though
diff --git a/modules/shared.py b/modules/shared.py
index d4ddeea0..671d30e1 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -356,6 +356,7 @@ options_templates.update(options_section(('training', "Training"), {
 options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": list_checkpoint_tiles()}, refresh=refresh_checkpoints),
     "sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
+    "sd_vae_checkpoint_cache": OptionInfo(0, "VAE Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
     "sd_vae": OptionInfo("auto", "SD VAE", gr.Dropdown, lambda: {"choices": sd_vae.vae_list}, refresh=sd_vae.refresh_vae_list),
     "sd_vae_as_default": OptionInfo(False, "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them"),
     "sd_hypernetwork": OptionInfo("None", "Hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),
-- 
cgit v1.2.3


From 463048344fc036b262aa132584b65ee6e9fec6cf Mon Sep 17 00:00:00 2001
From: Vladimir Mandic <mandic00@live.com>
Date: Fri, 30 Dec 2022 19:41:47 -0500
Subject: fix shared state dictionary

---
 modules/shared.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'modules/shared.py')

diff --git a/modules/shared.py b/modules/shared.py
index d4ddeea0..9a13fb60 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -168,7 +168,7 @@ class State:
     def dict(self):
         obj = {
             "skipped": self.skipped,
-            "interrupted": self.skipped,
+            "interrupted": self.interrupted,
             "job": self.job,
             "job_count": self.job_count,
             "job_no": self.job_no,
-- 
cgit v1.2.3


From f34c7341720fb2059992926c9f9ae6ff25f7385b Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Sat, 31 Dec 2022 18:06:35 +0300
Subject: alt-diffusion integration

---
 configs/alt-diffusion-inference.yaml   | 72 ++++++++++++++++++++++++++++++++++
 configs/altdiffusion/ad-inference.yaml | 72 ----------------------------------
 configs/v1-inference.yaml              | 70 +++++++++++++++++++++++++++++++++
 modules/sd_hijack.py                   | 18 +++++----
 modules/sd_hijack_clip.py              | 14 +++----
 modules/sd_hijack_xlmr.py              | 34 ++++++++++++++++
 modules/shared.py                      | 10 +----
 v1-inference.yaml                      | 70 ---------------------------------
 8 files changed, 192 insertions(+), 168 deletions(-)
 create mode 100644 configs/alt-diffusion-inference.yaml
 delete mode 100644 configs/altdiffusion/ad-inference.yaml
 create mode 100644 configs/v1-inference.yaml
 create mode 100644 modules/sd_hijack_xlmr.py
 delete mode 100644 v1-inference.yaml

(limited to 'modules/shared.py')

diff --git a/configs/alt-diffusion-inference.yaml b/configs/alt-diffusion-inference.yaml
new file mode 100644
index 00000000..cfbee72d
--- /dev/null
+++ b/configs/alt-diffusion-inference.yaml
@@ -0,0 +1,72 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: modules.xlmr.BertSeriesModelWithTransformation
+      params:
+        name: "XLMR-Large"
\ No newline at end of file
diff --git a/configs/altdiffusion/ad-inference.yaml b/configs/altdiffusion/ad-inference.yaml
deleted file mode 100644
index cfbee72d..00000000
--- a/configs/altdiffusion/ad-inference.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-model:
-  base_learning_rate: 1.0e-04
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: "jpg"
-    cond_stage_key: "txt"
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: false   # Note: different from the one we trained before
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [ 10000 ]
-        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
-        f_start: [ 1.e-6 ]
-        f_max: [ 1. ]
-        f_min: [ 1. ]
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32 # unused
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions: [ 4, 2, 1 ]
-        num_res_blocks: 2
-        channel_mult: [ 1, 2, 4, 4 ]
-        num_heads: 8
-        use_spatial_transformer: True
-        transformer_depth: 1
-        context_dim: 768
-        use_checkpoint: True
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: modules.xlmr.BertSeriesModelWithTransformation
-      params:
-        name: "XLMR-Large"
\ No newline at end of file
diff --git a/configs/v1-inference.yaml b/configs/v1-inference.yaml
new file mode 100644
index 00000000..d4effe56
--- /dev/null
+++ b/configs/v1-inference.yaml
@@ -0,0 +1,70 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py
index bce23b03..edcbaf52 100644
--- a/modules/sd_hijack.py
+++ b/modules/sd_hijack.py
@@ -5,7 +5,7 @@ import modules.textual_inversion.textual_inversion
 from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint
 from modules.hypernetworks import hypernetwork
 from modules.shared import cmd_opts
-from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet
+from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr
 
 from modules.sd_hijack_optimizations import invokeAI_mps_available
 
@@ -68,6 +68,7 @@ def fix_checkpoint():
     ldm.modules.diffusionmodules.openaimodel.ResBlock.forward = sd_hijack_checkpoint.ResBlock_forward
     ldm.modules.diffusionmodules.openaimodel.AttentionBlock.forward = sd_hijack_checkpoint.AttentionBlock_forward
 
+
 class StableDiffusionModelHijack:
     fixes = None
     comments = []
@@ -79,21 +80,22 @@ class StableDiffusionModelHijack:
 
     def hijack(self, m):
 
-        if shared.text_model_name == "XLMR-Large":
+        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
             model_embeddings = m.cond_stage_model.roberta.embeddings
             model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
-            m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
-            
+            m.cond_stage_model = sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords(m.cond_stage_model, self)
+
         elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder:
             model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
             model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self)
             m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
-            apply_optimizations()
+
         elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder:
             m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self)
             m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
-            apply_optimizations()
-        
+
+        apply_optimizations()
+
         self.clip = m.cond_stage_model
         
         fix_checkpoint()
@@ -109,7 +111,7 @@ class StableDiffusionModelHijack:
 
     def undo_hijack(self, m):
 
-        if shared.text_model_name == "XLMR-Large":
+        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
             m.cond_stage_model = m.cond_stage_model.wrapped 
 
         elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
diff --git a/modules/sd_hijack_clip.py b/modules/sd_hijack_clip.py
index 9ea6e1ce..6ec50cca 100644
--- a/modules/sd_hijack_clip.py
+++ b/modules/sd_hijack_clip.py
@@ -4,7 +4,6 @@ import torch
 
 from modules import prompt_parser, devices
 from modules.shared import opts
-import modules.shared as shared
 
 def get_target_prompt_token_count(token_count):
     return math.ceil(max(token_count, 1) / 75) * 75
@@ -177,9 +176,6 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
         return batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count
 
     def forward(self, text):
-        if shared.text_model_name == "XLMR-Large":
-            return self.wrapped.encode(text)
-
         use_old = opts.use_old_emphasis_implementation
         if use_old:
             batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count = self.process_text_old(text)
@@ -257,13 +253,13 @@ class FrozenCLIPEmbedderWithCustomWords(FrozenCLIPEmbedderWithCustomWordsBase):
     def __init__(self, wrapped, hijack):
         super().__init__(wrapped, hijack)
         self.tokenizer = wrapped.tokenizer
-        if shared.text_model_name == "XLMR-Large":
-            self.comma_token = None 
-        else :
-            self.comma_token = [v for k, v in self.tokenizer.get_vocab().items() if k == ',</w>'][0]
+
+        vocab = self.tokenizer.get_vocab()
+
+        self.comma_token = vocab.get(',</w>', None)
 
         self.token_mults = {}
-        tokens_with_parens = [(k, v) for k, v in self.tokenizer.get_vocab().items() if '(' in k or ')' in k or '[' in k or ']' in k]
+        tokens_with_parens = [(k, v) for k, v in vocab.items() if '(' in k or ')' in k or '[' in k or ']' in k]
         for text, ident in tokens_with_parens:
             mult = 1.0
             for c in text:
diff --git a/modules/sd_hijack_xlmr.py b/modules/sd_hijack_xlmr.py
new file mode 100644
index 00000000..4ac51c38
--- /dev/null
+++ b/modules/sd_hijack_xlmr.py
@@ -0,0 +1,34 @@
+import open_clip.tokenizer
+import torch
+
+from modules import sd_hijack_clip, devices
+from modules.shared import opts
+
+
+class FrozenXLMREmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords):
+    def __init__(self, wrapped, hijack):
+        super().__init__(wrapped, hijack)
+
+        self.id_start = wrapped.config.bos_token_id
+        self.id_end = wrapped.config.eos_token_id
+        self.id_pad = wrapped.config.pad_token_id
+
+        self.comma_token = self.tokenizer.get_vocab().get(',', None)  # alt diffusion doesn't have </w> bits for comma
+
+    def encode_with_transformers(self, tokens):
+        # there's no CLIP Skip here because all hidden layers have size of 1024 and the last one uses a
+        # trained layer to transform those 1024 into 768 for unet; so you can't choose which transformer
+        # layer to work with - you have to use the last
+
+        attention_mask = (tokens != self.id_pad).to(device=tokens.device, dtype=torch.int64)
+        features = self.wrapped(input_ids=tokens, attention_mask=attention_mask)
+        z = features['projection_state']
+
+        return z
+
+    def encode_embedding_init_text(self, init_text, nvpt):
+        embedding_layer = self.wrapped.roberta.embeddings
+        ids = self.wrapped.tokenizer(init_text, max_length=nvpt, return_tensors="pt", add_special_tokens=False)["input_ids"]
+        embedded = embedding_layer.token_embedding.wrapped(ids.to(devices.device)).squeeze(0)
+
+        return embedded
diff --git a/modules/shared.py b/modules/shared.py
index 2b31e717..715b9169 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -23,7 +23,7 @@ demo = None
 sd_model_file = os.path.join(script_path, 'model.ckpt')
 default_sd_model_file = sd_model_file
 parser = argparse.ArgumentParser()
-parser.add_argument("--config", type=str, default=os.path.join(script_path, "v1-inference.yaml"), help="path to config which constructs model",)
+parser.add_argument("--config", type=str, default=os.path.join(script_path, "configs/v1-inference.yaml"), help="path to config which constructs model",)
 parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
 parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
 parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
@@ -108,14 +108,6 @@ restricted_opts = {
     "outdir_txt2img_grids",
     "outdir_save",
 }
-from omegaconf import OmegaConf
-config = OmegaConf.load(f"{cmd_opts.config}")
-# XLMR-Large
-try:
-    text_model_name = config.model.params.cond_stage_config.params.name
-
-except :
-    text_model_name = "stable_diffusion"
 
 cmd_opts.disable_extension_access = (cmd_opts.share or cmd_opts.listen or cmd_opts.server_name) and not cmd_opts.enable_insecure_extension_access
 
diff --git a/v1-inference.yaml b/v1-inference.yaml
deleted file mode 100644
index d4effe56..00000000
--- a/v1-inference.yaml
+++ /dev/null
@@ -1,70 +0,0 @@
-model:
-  base_learning_rate: 1.0e-04
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: "jpg"
-    cond_stage_key: "txt"
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: false   # Note: different from the one we trained before
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [ 10000 ]
-        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
-        f_start: [ 1.e-6 ]
-        f_max: [ 1. ]
-        f_min: [ 1. ]
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32 # unused
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions: [ 4, 2, 1 ]
-        num_res_blocks: 2
-        channel_mult: [ 1, 2, 4, 4 ]
-        num_heads: 8
-        use_spatial_transformer: True
-        transformer_depth: 1
-        context_dim: 768
-        use_checkpoint: True
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
-- 
cgit v1.2.3


From 29a3a7eb13478297bc7093971b48827ab8246f45 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Sun, 1 Jan 2023 01:19:10 +0300
Subject: show sampler selection in dropdown, add option selection to revert to
 old radio group

---
 modules/shared.py |  1 +
 modules/ui.py     | 22 +++++++++++++++-------
 2 files changed, 16 insertions(+), 7 deletions(-)

(limited to 'modules/shared.py')

diff --git a/modules/shared.py b/modules/shared.py
index 715b9169..948b9542 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -406,6 +406,7 @@ options_templates.update(options_section(('ui', "User interface"), {
     "js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),
     "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
     "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
+    "samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group"),
     'quicksettings': OptionInfo("sd_model_checkpoint", "Quicksettings list"),
     'localization': OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)),
 }))
diff --git a/modules/ui.py b/modules/ui.py
index 279b5110..c7b8ea5d 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -643,6 +643,19 @@ Requested path was: {f}
                 return result_gallery, generation_info if tabname != "extras" else html_info_x, html_info, html_log
 
 
+def create_sampler_and_steps_selection(choices, tabname):
+    if opts.samplers_in_dropdown:
+        with gr.Row(elem_id=f"sampler_selection_{tabname}"):
+            sampler_index = gr.Dropdown(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
+            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+    else:
+        with gr.Group(elem_id=f"sampler_selection_{tabname}"):
+            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+            sampler_index = gr.Radio(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
+
+    return steps, sampler_index
+
+
 def create_ui():
     import modules.img2img
     import modules.txt2img
@@ -660,9 +673,6 @@ def create_ui():
         dummy_component = gr.Label(visible=False)
         txt_prompt_img = gr.File(label="", elem_id="txt2img_prompt_image", file_count="single", type="bytes", visible=False)
 
-
-
-
         with gr.Row(elem_id='txt2img_progress_row'):
             with gr.Column(scale=1):
                 pass
@@ -674,8 +684,7 @@ def create_ui():
 
         with gr.Row().style(equal_height=False):
             with gr.Column(variant='panel', elem_id="txt2img_settings"):
-                steps = gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=20)
-                sampler_index = gr.Radio(label='Sampling method', elem_id="txt2img_sampling", choices=[x.name for x in samplers], value=samplers[0].name, type="index")
+                steps, sampler_index = create_sampler_and_steps_selection(samplers, "txt2img")
 
                 with gr.Group():
                     width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
@@ -875,8 +884,7 @@ def create_ui():
                 with gr.Row():
                     resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", show_label=False, choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
 
-                steps = gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=20)
-                sampler_index = gr.Radio(label='Sampling method', choices=[x.name for x in samplers_for_img2img], value=samplers_for_img2img[0].name, type="index")
+                steps, sampler_index = create_sampler_and_steps_selection(samplers_for_img2img, "img2img")
 
                 with gr.Group():
                     width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
-- 
cgit v1.2.3


From 16b9661d2741b241c3964fcbd56559c078b84822 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Sun, 1 Jan 2023 09:51:37 +0300
Subject: change karras scheduler sigmas to values recommended by SD from old
 0.1 to 10 with an option to revert to old

---
 modules/sd_samplers.py | 4 +++-
 modules/shared.py      | 6 +++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'modules/shared.py')

diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py
index 177b5338..e904d860 100644
--- a/modules/sd_samplers.py
+++ b/modules/sd_samplers.py
@@ -465,7 +465,9 @@ class KDiffusionSampler:
         if p.sampler_noise_scheduler_override:
             sigmas = p.sampler_noise_scheduler_override(steps)
         elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
-            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=0.1, sigma_max=10, device=shared.device)
+            sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
+
+            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=sigma_min, sigma_max=sigma_max, device=shared.device)
         else:
             sigmas = self.model_wrap.get_sigmas(steps)
 
diff --git a/modules/shared.py b/modules/shared.py
index 948b9542..7f430b93 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -368,13 +368,17 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "img2img_background_color": OptionInfo("#ffffff", "With img2img, fill image's transparent parts with this color.", gr.ColorPicker, {}),
     "enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply."),
     "enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"),
-    "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
     "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),
     "comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }),
     'CLIP_stop_at_last_layers': OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),
     "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
 }))
 
+options_templates.update(options_section(('compatibility', "Compatibility"), {
+    "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
+    "use_old_karras_scheduler_sigmas": OptionInfo(False, "Use old karras scheduler sigmas (0.1 to 10)."),
+}))
+
 options_templates.update(options_section(('interrogate', "Interrogate Options"), {
     "interrogate_keep_models_in_memory": OptionInfo(False, "Interrogate: keep models in VRAM"),
     "interrogate_use_builtin_artists": OptionInfo(True, "Interrogate: use artists from artists.csv"),
-- 
cgit v1.2.3


From ef27a18b6b7cb1a8eebdc9b2e88d25baf2c2414d Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Mon, 2 Jan 2023 19:42:10 +0300
Subject: Hires fix rework

---
 modules/generation_parameters_copypaste.py | 32 ++++++++++++++
 modules/images.py                          | 24 +++++++++--
 modules/processing.py                      | 68 ++++++++++++------------------
 modules/shared.py                          |  7 ++-
 modules/txt2img.py                         |  6 +--
 modules/ui.py                              | 15 +++----
 scripts/xy_grid.py                         |  4 +-
 7 files changed, 96 insertions(+), 60 deletions(-)

(limited to 'modules/shared.py')

diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py
index 8e7f0df0..d6fa822b 100644
--- a/modules/generation_parameters_copypaste.py
+++ b/modules/generation_parameters_copypaste.py
@@ -1,5 +1,6 @@
 import base64
 import io
+import math
 import os
 import re
 from pathlib import Path
@@ -164,6 +165,35 @@ def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
     return None
 
 
+def restore_old_hires_fix_params(res):
+    """for infotexts that specify old First pass size parameter, convert it into
+    width, height, and hr scale"""
+
+    firstpass_width = res.get('First pass size-1', None)
+    firstpass_height = res.get('First pass size-2', None)
+
+    if firstpass_width is None or firstpass_height is None:
+        return
+
+    firstpass_width, firstpass_height = int(firstpass_width), int(firstpass_height)
+    width = int(res.get("Size-1", 512))
+    height = int(res.get("Size-2", 512))
+
+    if firstpass_width == 0 or firstpass_height == 0:
+        # old algorithm for auto-calculating first pass size
+        desired_pixel_count = 512 * 512
+        actual_pixel_count = width * height
+        scale = math.sqrt(desired_pixel_count / actual_pixel_count)
+        firstpass_width = math.ceil(scale * width / 64) * 64
+        firstpass_height = math.ceil(scale * height / 64) * 64
+
+    hr_scale = width / firstpass_width if firstpass_width > 0 else height / firstpass_height
+
+    res['Size-1'] = firstpass_width
+    res['Size-2'] = firstpass_height
+    res['Hires upscale'] = hr_scale
+
+
 def parse_generation_parameters(x: str):
     """parses generation parameters string, the one you see in text field under the picture in UI:
 ```
@@ -221,6 +251,8 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         hypernet_hash = res.get("Hypernet hash", None)
         res["Hypernet"] = find_hypernetwork_key(hypernet_name, hypernet_hash)
 
+    restore_old_hires_fix_params(res)
+
     return res
 
 
diff --git a/modules/images.py b/modules/images.py
index f84fd485..c3a5fc8b 100644
--- a/modules/images.py
+++ b/modules/images.py
@@ -230,16 +230,32 @@ def draw_prompt_matrix(im, width, height, all_prompts):
     return draw_grid_annotations(im, width, height, hor_texts, ver_texts)
 
 
-def resize_image(resize_mode, im, width, height):
+def resize_image(resize_mode, im, width, height, upscaler_name=None):
+    """
+    Resizes an image with the specified resize_mode, width, and height.
+
+    Args:
+        resize_mode: The mode to use when resizing the image.
+            0: Resize the image to the specified width and height.
+            1: Resize the image to fill the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, cropping the excess.
+            2: Resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, filling empty with data from image.
+        im: The image to resize.
+        width: The width to resize the image to.
+        height: The height to resize the image to.
+        upscaler_name: The name of the upscaler to use. If not provided, defaults to opts.upscaler_for_img2img.
+    """
+
+    upscaler_name = upscaler_name or opts.upscaler_for_img2img
+
     def resize(im, w, h):
-        if opts.upscaler_for_img2img is None or opts.upscaler_for_img2img == "None" or im.mode == 'L':
+        if upscaler_name is None or upscaler_name == "None" or im.mode == 'L':
             return im.resize((w, h), resample=LANCZOS)
 
         scale = max(w / im.width, h / im.height)
 
         if scale > 1.0:
-            upscalers = [x for x in shared.sd_upscalers if x.name == opts.upscaler_for_img2img]
-            assert len(upscalers) > 0, f"could not find upscaler named {opts.upscaler_for_img2img}"
+            upscalers = [x for x in shared.sd_upscalers if x.name == upscaler_name]
+            assert len(upscalers) > 0, f"could not find upscaler named {upscaler_name}"
 
             upscaler = upscalers[0]
             im = upscaler.scaler.upscale(im, scale, upscaler.data_path)
diff --git a/modules/processing.py b/modules/processing.py
index 42dc19ea..4654570c 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -658,14 +658,18 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     sampler = None
 
-    def __init__(self, enable_hr: bool=False, denoising_strength: float=0.75, firstphase_width: int=0, firstphase_height: int=0, **kwargs):
+    def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, **kwargs):
         super().__init__(**kwargs)
         self.enable_hr = enable_hr
         self.denoising_strength = denoising_strength
-        self.firstphase_width = firstphase_width
-        self.firstphase_height = firstphase_height
-        self.truncate_x = 0
-        self.truncate_y = 0
+        self.hr_scale = hr_scale
+        self.hr_upscaler = hr_upscaler
+
+        if firstphase_width != 0 or firstphase_height != 0:
+            print("firstphase_width/firstphase_height no longer supported; use hr_scale", file=sys.stderr)
+            self.hr_scale = self.width / firstphase_width
+            self.width = firstphase_width
+            self.height = firstphase_height
 
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
@@ -674,47 +678,29 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             else:
                 state.job_count = state.job_count * 2
 
-            self.extra_generation_params["First pass size"] = f"{self.firstphase_width}x{self.firstphase_height}"
-
-            if self.firstphase_width == 0 or self.firstphase_height == 0:
-                desired_pixel_count = 512 * 512
-                actual_pixel_count = self.width * self.height
-                scale = math.sqrt(desired_pixel_count / actual_pixel_count)
-                self.firstphase_width = math.ceil(scale * self.width / 64) * 64
-                self.firstphase_height = math.ceil(scale * self.height / 64) * 64
-                firstphase_width_truncated = int(scale * self.width)
-                firstphase_height_truncated = int(scale * self.height)
-
-            else:
-
-                width_ratio = self.width / self.firstphase_width
-                height_ratio = self.height / self.firstphase_height
-
-                if width_ratio > height_ratio:
-                    firstphase_width_truncated = self.firstphase_width
-                    firstphase_height_truncated = self.firstphase_width * self.height / self.width
-                else:
-                    firstphase_width_truncated = self.firstphase_height * self.width / self.height
-                    firstphase_height_truncated = self.firstphase_height
-
-            self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f
-            self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f
+            self.extra_generation_params["Hires upscale"] = self.hr_scale
+            if self.hr_upscaler is not None:
+                self.extra_generation_params["Hires upscaler"] = self.hr_upscaler
 
     def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
         self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
 
+        latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_default_mode
+        if self.enable_hr and latent_scale_mode is None:
+            assert len([x for x in shared.sd_upscalers if x.name == self.hr_upscaler]) > 0, f"could not find upscaler named {self.hr_upscaler}"
+
+        x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
+        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
+
         if not self.enable_hr:
-            x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-            samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
             return samples
 
-        x = create_random_tensors([opt_C, self.firstphase_height // opt_f, self.firstphase_width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x, self.firstphase_width, self.firstphase_height))
-
-        samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]
+        target_width = int(self.width * self.hr_scale)
+        target_height = int(self.height * self.hr_scale)
 
-        """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
         def save_intermediate(image, index):
+            """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
+
             if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix:
                 return
 
@@ -723,11 +709,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
             images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
 
-        if opts.use_scale_latent_for_hires_fix:
+        if latent_scale_mode is not None:
             for i in range(samples.shape[0]):
                 save_intermediate(samples, i)
 
-            samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
+            samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode)
 
             # Avoid making the inpainting conditioning unless necessary as
             # this does need some extra compute to decode / encode the image again.
@@ -747,7 +733,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
                 save_intermediate(image, i)
 
-                image = images.resize_image(0, image, self.width, self.height)
+                image = images.resize_image(0, image, target_width, target_height, upscaler_name=self.hr_upscaler)
                 image = np.array(image).astype(np.float32) / 255.0
                 image = np.moveaxis(image, 2, 0)
                 batch_images.append(image)
@@ -764,7 +750,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
 
-        noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
+        noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, p=self)
 
         # GC now before running the next img2img to prevent running out of memory
         x = None
diff --git a/modules/shared.py b/modules/shared.py
index 7f430b93..b65559ee 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -327,7 +327,6 @@ options_templates.update(options_section(('upscaling', "Upscaling"), {
     "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
     "realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI. (Requires restart)", gr.CheckboxGroup, lambda: {"choices": realesrgan_models_names()}),
     "upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in sd_upscalers]}),
-    "use_scale_latent_for_hires_fix": OptionInfo(False, "Upscale latent space image when doing hires. fix"),
 }))
 
 options_templates.update(options_section(('face-restoration', "Face restoration"), {
@@ -545,6 +544,12 @@ opts = Options()
 if os.path.exists(config_filename):
     opts.load(config_filename)
 
+latent_upscale_default_mode = "Latent"
+latent_upscale_modes = {
+    "Latent": "bilinear",
+    "Latent (nearest)": "nearest",
+}
+
 sd_upscalers = []
 
 sd_model = None
diff --git a/modules/txt2img.py b/modules/txt2img.py
index 7f61e19a..e189a899 100644
--- a/modules/txt2img.py
+++ b/modules/txt2img.py
@@ -8,7 +8,7 @@ import modules.processing as processing
 from modules.ui import plaintext_to_html
 
 
-def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, firstphase_width: int, firstphase_height: int, *args):
+def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, *args):
     p = StableDiffusionProcessingTxt2Img(
         sd_model=shared.sd_model,
         outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
@@ -33,8 +33,8 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
         tiling=tiling,
         enable_hr=enable_hr,
         denoising_strength=denoising_strength if enable_hr else None,
-        firstphase_width=firstphase_width if enable_hr else None,
-        firstphase_height=firstphase_height if enable_hr else None,
+        hr_scale=hr_scale,
+        hr_upscaler=hr_upscaler,
     )
 
     p.scripts = modules.scripts.scripts_txt2img
diff --git a/modules/ui.py b/modules/ui.py
index 7070ea15..27cd9ddd 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -684,11 +684,11 @@ def create_ui():
                 with gr.Row():
                     restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
                     tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
-                    enable_hr = gr.Checkbox(label='Highres. fix', value=False, elem_id="txt2img_enable_hr")
+                    enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
 
                 with gr.Row(visible=False) as hr_options:
-                    firstphase_width = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass width", value=0, elem_id="txt2img_firstphase_width")
-                    firstphase_height = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass height", value=0, elem_id="txt2img_firstphase_height")
+                    hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
+                    hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
                     denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
 
                 with gr.Row(equal_height=True):
@@ -729,8 +729,8 @@ def create_ui():
                     width,
                     enable_hr,
                     denoising_strength,
-                    firstphase_width,
-                    firstphase_height,
+                    hr_scale,
+                    hr_upscaler,
                 ] + custom_inputs,
 
                 outputs=[
@@ -762,7 +762,6 @@ def create_ui():
                 outputs=[hr_options],
             )
 
-
             txt2img_paste_fields = [
                 (txt2img_prompt, "Prompt"),
                 (txt2img_negative_prompt, "Negative prompt"),
@@ -781,8 +780,8 @@ def create_ui():
                 (denoising_strength, "Denoising strength"),
                 (enable_hr, lambda d: "Denoising strength" in d),
                 (hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
-                (firstphase_width, "First pass size-1"),
-                (firstphase_height, "First pass size-2"),
+                (hr_scale, "Hires upscale"),
+                (hr_upscaler, "Hires upscaler"),
                 *modules.scripts.scripts_txt2img.infotext_fields
             ]
             parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields)
diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py
index 3e0b2805..f92f9776 100644
--- a/scripts/xy_grid.py
+++ b/scripts/xy_grid.py
@@ -202,7 +202,7 @@ axis_options = [
     AxisOption("Eta", float, apply_field("eta"), format_value_add_label, None),
     AxisOption("Clip skip", int, apply_clip_skip, format_value_add_label, None),
     AxisOption("Denoising", float, apply_field("denoising_strength"), format_value_add_label, None),
-    AxisOption("Upscale latent space for hires.", str, apply_upscale_latent_space, format_value_add_label, None),
+    AxisOption("Hires upscaler", str, apply_field("hr_upscaler"), format_value_add_label, None),
     AxisOption("Cond. Image Mask Weight", float, apply_field("inpainting_mask_weight"), format_value_add_label, None),
     AxisOption("VAE", str, apply_vae, format_value_add_label, None),
     AxisOption("Styles", str, apply_styles, format_value_add_label, None),
@@ -267,7 +267,6 @@ class SharedSettingsStackHelper(object):
         self.CLIP_stop_at_last_layers = opts.CLIP_stop_at_last_layers
         self.hypernetwork = opts.sd_hypernetwork
         self.model = shared.sd_model
-        self.use_scale_latent_for_hires_fix = opts.use_scale_latent_for_hires_fix
         self.vae = opts.sd_vae
   
     def __exit__(self, exc_type, exc_value, tb):
@@ -278,7 +277,6 @@ class SharedSettingsStackHelper(object):
         hypernetwork.apply_strength()
 
         opts.data["CLIP_stop_at_last_layers"] = self.CLIP_stop_at_last_layers
-        opts.data["use_scale_latent_for_hires_fix"] = self.use_scale_latent_for_hires_fix
 
 
 re_range = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\(([+-]\d+)\s*\))?\s*")
-- 
cgit v1.2.3


From a1cf55a9d1c82f8e56c00d549bca5c8fa069f412 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Tue, 3 Jan 2023 10:39:21 +0300
Subject: add option to reorder items in main UI

---
 modules/shared.py |  13 ++++++
 modules/ui.py     | 130 +++++++++++++++++++++++++++++++++++-------------------
 2 files changed, 97 insertions(+), 46 deletions(-)

(limited to 'modules/shared.py')

diff --git a/modules/shared.py b/modules/shared.py
index b65559ee..23657a93 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -109,6 +109,17 @@ restricted_opts = {
     "outdir_save",
 }
 
+ui_reorder_categories = [
+    "sampler",
+    "dimensions",
+    "cfg",
+    "seed",
+    "checkboxes",
+    "hires_fix",
+    "batch",
+    "scripts",
+]
+
 cmd_opts.disable_extension_access = (cmd_opts.share or cmd_opts.listen or cmd_opts.server_name) and not cmd_opts.enable_insecure_extension_access
 
 devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_esrgan, devices.device_codeformer = \
@@ -410,7 +421,9 @@ options_templates.update(options_section(('ui', "User interface"), {
     "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
     "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
     "samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group"),
+    "dimensions_and_batch_together": OptionInfo(True, "Show Witdth/Height and Batch sliders in same row"),
     'quicksettings': OptionInfo("sd_model_checkpoint", "Quicksettings list"),
+    'ui_reorder': OptionInfo(", ".join(ui_reorder_categories), "txt2img/ing2img UI item order"),
     'localization': OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)),
 }))
 
diff --git a/modules/ui.py b/modules/ui.py
index 2c92c422..f2e7c0d6 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -644,6 +644,13 @@ def create_sampler_and_steps_selection(choices, tabname):
     return steps, sampler_index
 
 
+def ordered_ui_categories():
+    user_order = {x.strip(): i for i, x in enumerate(shared.opts.ui_reorder.split(","))}
+
+    for i, category in sorted(enumerate(shared.ui_reorder_categories), key=lambda x: user_order.get(x[1], x[0] + 1000)):
+        yield category
+
+
 def create_ui():
     import modules.img2img
     import modules.txt2img
@@ -672,32 +679,48 @@ def create_ui():
 
         with gr.Row().style(equal_height=False):
             with gr.Column(variant='panel', elem_id="txt2img_settings"):
-                steps, sampler_index = create_sampler_and_steps_selection(samplers, "txt2img")
-
-                with FormRow():
-                    with gr.Column(elem_id="txt2img_column_size", scale=4):
-                        width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="txt2img_width")
-                        height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
-                    with gr.Column(elem_id="txt2img_column_batch"):
-                        batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
-                        batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
-
-                cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
-
-                seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('txt2img')
-
-                with FormRow(elem_id="txt2img_checkboxes"):
-                    restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
-                    tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
-                    enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
+                for category in ordered_ui_categories():
+                    if category == "sampler":
+                        steps, sampler_index = create_sampler_and_steps_selection(samplers, "txt2img")
 
-                with FormRow(visible=False) as hr_options:
-                    hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
-                    hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
-                    denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
-
-                with FormGroup(elem_id="txt2img_script_container"):
-                    custom_inputs = modules.scripts.scripts_txt2img.setup_ui()
+                    elif category == "dimensions":
+                        with FormRow():
+                            with gr.Column(elem_id="txt2img_column_size", scale=4):
+                                width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="txt2img_width")
+                                height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
+
+                            if opts.dimensions_and_batch_together:
+                                with gr.Column(elem_id="txt2img_column_batch"):
+                                    batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
+                                    batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
+
+                    elif category == "cfg":
+                        cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
+
+                    elif category == "seed":
+                        seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('txt2img')
+
+                    elif category == "checkboxes":
+                        with FormRow(elem_id="txt2img_checkboxes"):
+                            restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
+                            tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
+                            enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
+
+                    elif category == "hires_fix":
+                        with FormRow(visible=False, elem_id="txt2img_hires_fix") as hr_options:
+                            hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
+                            hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
+                            denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
+
+                    elif category == "batch":
+                        if not opts.dimensions_and_batch_together:
+                            with FormRow(elem_id="txt2img_column_batch"):
+                                batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
+                                batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
+
+                    elif category == "scripts":
+                        with FormGroup(elem_id="txt2img_script_container"):
+                            custom_inputs = modules.scripts.scripts_txt2img.setup_ui()
 
             txt2img_gallery, generation_info, html_info, html_log = create_output_panel("txt2img", opts.outdir_txt2img_samples)
             parameters_copypaste.bind_buttons({"txt2img": txt2img_paste}, None, txt2img_prompt)
@@ -865,28 +888,43 @@ def create_ui():
                 with FormRow():
                     resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
 
-                steps, sampler_index = create_sampler_and_steps_selection(samplers_for_img2img, "img2img")
-
-                with FormRow():
-                    with gr.Column(elem_id="img2img_column_size", scale=4):
-                        width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
-                        height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
-                    with gr.Column(elem_id="img2img_column_batch"):
-                        batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
-                        batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
-
-                with FormGroup():
-                    cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
-                    denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75, elem_id="img2img_denoising_strength")
-
-                seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('img2img')
+                for category in ordered_ui_categories():
+                    if category == "sampler":
+                        steps, sampler_index = create_sampler_and_steps_selection(samplers_for_img2img, "img2img")
 
-                with FormRow(elem_id="img2img_checkboxes"):
-                    restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="img2img_restore_faces")
-                    tiling = gr.Checkbox(label='Tiling', value=False, elem_id="img2img_tiling")
-
-                with FormGroup(elem_id="img2img_script_container"):
-                    custom_inputs = modules.scripts.scripts_img2img.setup_ui()
+                    elif category == "dimensions":
+                        with FormRow():
+                            with gr.Column(elem_id="img2img_column_size", scale=4):
+                                width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
+                                height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
+
+                            if opts.dimensions_and_batch_together:
+                                with gr.Column(elem_id="img2img_column_batch"):
+                                    batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
+                                    batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
+
+                    elif category == "cfg":
+                        with FormGroup():
+                            cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
+                            denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75, elem_id="img2img_denoising_strength")
+
+                    elif category == "seed":
+                        seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('img2img')
+
+                    elif category == "checkboxes":
+                        with FormRow(elem_id="img2img_checkboxes"):
+                            restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="img2img_restore_faces")
+                            tiling = gr.Checkbox(label='Tiling', value=False, elem_id="img2img_tiling")
+
+                    elif category == "batch":
+                        if not opts.dimensions_and_batch_together:
+                            with FormRow(elem_id="img2img_column_batch"):
+                                batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
+                                batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
+
+                    elif category == "scripts":
+                        with FormGroup(elem_id="img2img_script_container"):
+                            custom_inputs = modules.scripts.scripts_img2img.setup_ui()
 
             img2img_gallery, generation_info, html_info, html_log = create_output_panel("img2img", opts.outdir_img2img_samples)
             parameters_copypaste.bind_buttons({"img2img": img2img_paste}, None, img2img_prompt)
-- 
cgit v1.2.3