diff options
77 files changed, 1415 insertions, 4246 deletions
diff --git a/.github/workflows/run_tests.yaml b/.github/workflows/run_tests.yaml index 3dafaf8d..f42e4758 100644 --- a/.github/workflows/run_tests.yaml +++ b/.github/workflows/run_tests.yaml @@ -20,6 +20,12 @@ jobs: cache-dependency-path: | **/requirements*txt launch.py + - name: Cache models + id: cache-models + uses: actions/cache@v3 + with: + path: models + key: "2023-12-30" - name: Install test dependencies run: pip install wait-for-it -r requirements-test.txt env: @@ -33,6 +39,8 @@ jobs: TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu WEBUI_LAUNCH_LIVE_OUTPUT: "1" PYTHONUNBUFFERED: "1" + - name: Print installed packages + run: pip freeze - name: Start test server run: > python -m coverage run @@ -49,7 +57,7 @@ jobs: 2>&1 | tee output.txt & - name: Run tests run: | - wait-for-it --service 127.0.0.1:7860 -t 600 + wait-for-it --service 127.0.0.1:7860 -t 20 python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test - name: Kill test server if: always() @@ -37,3 +37,4 @@ notification.mp3 /node_modules /package-lock.json /.coverage* +/test/test_outputs diff --git a/configs/sd_xl_inpaint.yaml b/configs/sd_xl_inpaint.yaml new file mode 100644 index 00000000..3bad3721 --- /dev/null +++ b/configs/sd_xl_inpaint.yaml @@ -0,0 +1,98 @@ +model: + target: sgm.models.diffusion.DiffusionEngine + params: + scale_factor: 0.13025 + disable_first_stage_autocast: True + + denoiser_config: + target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser + params: + num_idx: 1000 + + weighting_config: + target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting + scaling_config: + target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling + discretization_config: + target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization + + network_config: + target: sgm.modules.diffusionmodules.openaimodel.UNetModel + params: + adm_in_channels: 2816 + num_classes: sequential + use_checkpoint: True + in_channels: 9 + out_channels: 4 + model_channels: 320 + attention_resolutions: [4, 2] + num_res_blocks: 2 + channel_mult: [1, 2, 4] + num_head_channels: 64 + use_spatial_transformer: True + use_linear_in_transformer: True + transformer_depth: [1, 2, 10] # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16 + context_dim: 2048 + spatial_transformer_attn_type: softmax-xformers + legacy: False + + conditioner_config: + target: sgm.modules.GeneralConditioner + params: + emb_models: + # crossattn cond + - is_trainable: False + input_key: txt + target: sgm.modules.encoders.modules.FrozenCLIPEmbedder + params: + layer: hidden + layer_idx: 11 + # crossattn and vector cond + - is_trainable: False + input_key: txt + target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2 + params: + arch: ViT-bigG-14 + version: laion2b_s39b_b160k + freeze: True + layer: penultimate + always_return_pooled: True + legacy: False + # vector cond + - is_trainable: False + input_key: original_size_as_tuple + target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND + params: + outdim: 256 # multiplied by two + # vector cond + - is_trainable: False + input_key: crop_coords_top_left + target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND + params: + outdim: 256 # multiplied by two + # vector cond + - is_trainable: False + input_key: target_size_as_tuple + target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND + params: + outdim: 256 # multiplied by two + + first_stage_config: + target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + attn_type: vanilla-xformers + 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 diff --git a/extensions-builtin/Lora/networks.py b/extensions-builtin/Lora/networks.py index 985b2753..72ebd624 100644 --- a/extensions-builtin/Lora/networks.py +++ b/extensions-builtin/Lora/networks.py @@ -1,3 +1,4 @@ +import gradio as gr
import logging
import os
import re
@@ -314,7 +315,12 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No emb_db.skipped_embeddings[name] = embedding
if failed_to_load_networks:
- sd_hijack.model_hijack.comments.append("Networks not found: " + ", ".join(failed_to_load_networks))
+ lora_not_found_message = f'Lora not found: {", ".join(failed_to_load_networks)}'
+ sd_hijack.model_hijack.comments.append(lora_not_found_message)
+ if shared.opts.lora_not_found_warning_console:
+ print(f'\n{lora_not_found_message}\n')
+ if shared.opts.lora_not_found_gradio_warning:
+ gr.Warning(lora_not_found_message)
purge_networks_from_memory()
diff --git a/extensions-builtin/Lora/scripts/lora_script.py b/extensions-builtin/Lora/scripts/lora_script.py index ef23968c..1518f7e5 100644 --- a/extensions-builtin/Lora/scripts/lora_script.py +++ b/extensions-builtin/Lora/scripts/lora_script.py @@ -39,6 +39,8 @@ shared.options_templates.update(shared.options_section(('extra_networks', "Extra "lora_show_all": shared.OptionInfo(False, "Always show all networks on the Lora page").info("otherwise, those detected as for incompatible version of Stable Diffusion will be hidden"),
"lora_hide_unknown_for_versions": shared.OptionInfo([], "Hide networks of unknown versions for model versions", gr.CheckboxGroup, {"choices": ["SD1", "SD2", "SDXL"]}),
"lora_in_memory_limit": shared.OptionInfo(0, "Number of Lora networks to keep cached in memory", gr.Number, {"precision": 0}),
+ "lora_not_found_warning_console": shared.OptionInfo(False, "Lora not found warning in console"),
+ "lora_not_found_gradio_warning": shared.OptionInfo(False, "Lora not found warning popup in webui"),
}))
diff --git a/extensions-builtin/Lora/ui_edit_user_metadata.py b/extensions-builtin/Lora/ui_edit_user_metadata.py index c7011909..3160aecf 100644 --- a/extensions-builtin/Lora/ui_edit_user_metadata.py +++ b/extensions-builtin/Lora/ui_edit_user_metadata.py @@ -54,12 +54,13 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) self.slider_preferred_weight = None
self.edit_notes = None
- def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, notes):
+ def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, negative_text, notes):
user_metadata = self.get_user_metadata(name)
user_metadata["description"] = desc
user_metadata["sd version"] = sd_version
user_metadata["activation text"] = activation_text
user_metadata["preferred weight"] = preferred_weight
+ user_metadata["negative text"] = negative_text
user_metadata["notes"] = notes
self.write_user_metadata(name, user_metadata)
@@ -127,6 +128,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) gr.HighlightedText.update(value=gradio_tags, visible=True if tags else False),
user_metadata.get('activation text', ''),
float(user_metadata.get('preferred weight', 0.0)),
+ user_metadata.get('negative text', ''),
gr.update(visible=True if tags else False),
gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
]
@@ -162,7 +164,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) self.taginfo = gr.HighlightedText(label="Training dataset tags")
self.edit_activation_text = gr.Text(label='Activation text', info="Will be added to prompt along with Lora")
self.slider_preferred_weight = gr.Slider(label='Preferred weight', info="Set to 0 to disable", minimum=0.0, maximum=2.0, step=0.01)
-
+ self.edit_negative_text = gr.Text(label='Negative prompt', info="Will be added to negative prompts")
with gr.Row() as row_random_prompt:
with gr.Column(scale=8):
random_prompt = gr.Textbox(label='Random prompt', lines=4, max_lines=4, interactive=False)
@@ -198,6 +200,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) self.taginfo,
self.edit_activation_text,
self.slider_preferred_weight,
+ self.edit_negative_text,
row_random_prompt,
random_prompt,
]
@@ -211,7 +214,9 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) self.select_sd_version,
self.edit_activation_text,
self.slider_preferred_weight,
+ self.edit_negative_text,
self.edit_notes,
]
+
self.setup_save_handler(self.button_save, self.save_lora_user_metadata, edited_components)
diff --git a/extensions-builtin/Lora/ui_extra_networks_lora.py b/extensions-builtin/Lora/ui_extra_networks_lora.py index df02c663..e714fac4 100644 --- a/extensions-builtin/Lora/ui_extra_networks_lora.py +++ b/extensions-builtin/Lora/ui_extra_networks_lora.py @@ -45,6 +45,11 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): if activation_text:
item["prompt"] += " + " + quote_js(" " + activation_text)
+ negative_prompt = item["user_metadata"].get("negative text")
+ item["negative_prompt"] = quote_js("")
+ if negative_prompt:
+ item["negative_prompt"] = quote_js('(' + negative_prompt + ':1)')
+
sd_version = item["user_metadata"].get("sd version")
if sd_version in network.SdVersion.__members__:
item["sd_version"] = sd_version
diff --git a/extensions-builtin/ScuNET/scripts/scunet_model.py b/extensions-builtin/ScuNET/scripts/scunet_model.py index 167d2f64..f799cb76 100644 --- a/extensions-builtin/ScuNET/scripts/scunet_model.py +++ b/extensions-builtin/ScuNET/scripts/scunet_model.py @@ -3,14 +3,11 @@ import sys import PIL.Image import numpy as np import torch -from tqdm import tqdm import modules.upscaler from modules import devices, modelloader, script_callbacks, errors -from scunet_model_arch import SCUNet - -from modules.modelloader import load_file_from_url from modules.shared import opts +from modules.upscaler_utils import tiled_upscale_2 class UpscalerScuNET(modules.upscaler.Upscaler): @@ -42,47 +39,6 @@ class UpscalerScuNET(modules.upscaler.Upscaler): scalers.append(scaler_data2) self.scalers = scalers - @staticmethod - @torch.no_grad() - def tiled_inference(img, model): - # test the image tile by tile - h, w = img.shape[2:] - tile = opts.SCUNET_tile - tile_overlap = opts.SCUNET_tile_overlap - if tile == 0: - return model(img) - - device = devices.get_device_for('scunet') - assert tile % 8 == 0, "tile size should be a multiple of window_size" - sf = 1 - - stride = tile - tile_overlap - h_idx_list = list(range(0, h - tile, stride)) + [h - tile] - w_idx_list = list(range(0, w - tile, stride)) + [w - tile] - E = torch.zeros(1, 3, h * sf, w * sf, dtype=img.dtype, device=device) - W = torch.zeros_like(E, dtype=devices.dtype, device=device) - - with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="ScuNET tiles") as pbar: - for h_idx in h_idx_list: - - for w_idx in w_idx_list: - - in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile] - - out_patch = model(in_patch) - out_patch_mask = torch.ones_like(out_patch) - - E[ - ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf - ].add_(out_patch) - W[ - ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf - ].add_(out_patch_mask) - pbar.update(1) - output = E.div_(W) - - return output - def do_upscale(self, img: PIL.Image.Image, selected_file): devices.torch_gc() @@ -106,7 +62,16 @@ class UpscalerScuNET(modules.upscaler.Upscaler): _img[:, :, :h, :w] = torch_img # pad image torch_img = _img - torch_output = self.tiled_inference(torch_img, model).squeeze(0) + with torch.no_grad(): + torch_output = tiled_upscale_2( + torch_img, + model, + tile_size=opts.SCUNET_tile, + tile_overlap=opts.SCUNET_tile_overlap, + scale=1, + device=devices.get_device_for('scunet'), |