aboutsummaryrefslogtreecommitdiffstats
path: root/modules
diff options
context:
space:
mode:
Diffstat (limited to 'modules')
-rw-r--r--modules/api/api.py29
-rw-r--r--modules/errors.py25
-rw-r--r--modules/extras.py33
-rw-r--r--modules/generation_parameters_copypaste.py9
-rw-r--r--modules/hypernetworks/hypernetwork.py24
-rw-r--r--modules/interrogate.py4
-rw-r--r--modules/processing.py118
-rw-r--r--modules/sd_hijack.py12
-rw-r--r--modules/sd_hijack_inpainting.py5
-rw-r--r--modules/sd_models.py63
-rw-r--r--modules/sd_samplers.py5
-rw-r--r--modules/shared.py30
-rw-r--r--modules/textual_inversion/learn_schedule.py11
-rw-r--r--modules/textual_inversion/preprocess.py1
-rw-r--r--modules/textual_inversion/textual_inversion.py72
-rw-r--r--modules/txt2img.py5
-rw-r--r--modules/ui.py79
17 files changed, 390 insertions, 135 deletions
diff --git a/modules/api/api.py b/modules/api/api.py
index 9c670f00..48a70a44 100644
--- a/modules/api/api.py
+++ b/modules/api/api.py
@@ -1,11 +1,12 @@
import base64
import io
import time
+import datetime
import uvicorn
from threading import Lock
from io import BytesIO
from gradio.processing_utils import decode_base64_to_file
-from fastapi import APIRouter, Depends, FastAPI, HTTPException
+from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request, Response
from fastapi.security import HTTPBasic, HTTPBasicCredentials
from secrets import compare_digest
@@ -18,7 +19,7 @@ from modules.textual_inversion.textual_inversion import create_embedding, train_
from modules.textual_inversion.preprocess import preprocess
from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
from PIL import PngImagePlugin,Image
-from modules.sd_models import checkpoints_list
+from modules.sd_models import checkpoints_list, find_checkpoint_config
from modules.realesrgan_model import get_realesrgan_models
from modules import devices
from typing import List
@@ -67,6 +68,27 @@ def encode_pil_to_base64(image):
bytes_data = output_bytes.getvalue()
return base64.b64encode(bytes_data)
+def api_middleware(app: FastAPI):
+ @app.middleware("http")
+ async def log_and_time(req: Request, call_next):
+ ts = time.time()
+ res: Response = await call_next(req)
+ duration = str(round(time.time() - ts, 4))
+ res.headers["X-Process-Time"] = duration
+ endpoint = req.scope.get('path', 'err')
+ if shared.cmd_opts.api_log and endpoint.startswith('/sdapi'):
+ print('API {t} {code} {prot}/{ver} {method} {endpoint} {cli} {duration}'.format(
+ t = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f"),
+ code = res.status_code,
+ ver = req.scope.get('http_version', '0.0'),
+ cli = req.scope.get('client', ('0:0.0.0', 0))[0],
+ prot = req.scope.get('scheme', 'err'),
+ method = req.scope.get('method', 'err'),
+ endpoint = endpoint,
+ duration = duration,
+ ))
+ return res
+
class Api:
def __init__(self, app: FastAPI, queue_lock: Lock):
@@ -79,6 +101,7 @@ class Api:
self.router = APIRouter()
self.app = app
self.queue_lock = queue_lock
+ api_middleware(self.app)
self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse)
self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse)
self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse)
@@ -303,7 +326,7 @@ class Api:
return upscalers
def get_sd_models(self):
- return [{"title":x.title, "model_name":x.model_name, "hash":x.hash, "filename": x.filename, "config": x.config} for x in checkpoints_list.values()]
+ return [{"title":x.title, "model_name":x.model_name, "hash":x.hash, "filename": x.filename, "config": find_checkpoint_config(x)} for x in checkpoints_list.values()]
def get_hypernetworks(self):
return [{"name": name, "path": shared.hypernetworks[name]} for name in shared.hypernetworks]
diff --git a/modules/errors.py b/modules/errors.py
index 372dc51a..a668c014 100644
--- a/modules/errors.py
+++ b/modules/errors.py
@@ -2,9 +2,30 @@ import sys
import traceback
+def print_error_explanation(message):
+ lines = message.strip().split("\n")
+ max_len = max([len(x) for x in lines])
+
+ print('=' * max_len, file=sys.stderr)
+ for line in lines:
+ print(line, file=sys.stderr)
+ print('=' * max_len, file=sys.stderr)
+
+
+def display(e: Exception, task):
+ print(f"{task or 'error'}: {type(e).__name__}", file=sys.stderr)
+ print(traceback.format_exc(), file=sys.stderr)
+
+ message = str(e)
+ if "copying a param with shape torch.Size([640, 1024]) from checkpoint, the shape in current model is torch.Size([640, 768])" in message:
+ print_error_explanation("""
+The most likely cause of this is you are trying to load Stable Diffusion 2.0 model without specifying its connfig file.
+See https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20 for how to solve this.
+ """)
+
+
def run(code, task):
try:
code()
except Exception as e:
- print(f"{task}: {type(e).__name__}", file=sys.stderr)
- print(traceback.format_exc(), file=sys.stderr)
+ display(task, e)
diff --git a/modules/extras.py b/modules/extras.py
index 5e270250..7407bfe3 100644
--- a/modules/extras.py
+++ b/modules/extras.py
@@ -19,8 +19,6 @@ from modules.shared import opts
import modules.gfpgan_model
from modules.ui import plaintext_to_html
import modules.codeformer_model
-import piexif
-import piexif.helper
import gradio as gr
import safetensors.torch
@@ -58,6 +56,9 @@ cached_images: LruCache = LruCache(max_size=5)
def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility, upscale_first: bool, save_output: bool = True):
devices.torch_gc()
+ shared.state.begin()
+ shared.state.job = 'extras'
+
imageArr = []
# Also keep track of original file names
imageNameArr = []
@@ -94,6 +95,7 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
# Extra operation definitions
def run_gfpgan(image: Image.Image, info: str) -> Tuple[Image.Image, str]:
+ shared.state.job = 'extras-gfpgan'
restored_img = modules.gfpgan_model.gfpgan_fix_faces(np.array(image, dtype=np.uint8))
res = Image.fromarray(restored_img)
@@ -104,6 +106,7 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
return (res, info)
def run_codeformer(image: Image.Image, info: str) -> Tuple[Image.Image, str]:
+ shared.state.job = 'extras-codeformer'
restored_img = modules.codeformer_model.codeformer.restore(np.array(image, dtype=np.uint8), w=codeformer_weight)
res = Image.fromarray(restored_img)
@@ -114,6 +117,7 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
return (res, info)
def upscale(image, scaler_index, resize, mode, resize_w, resize_h, crop):
+ shared.state.job = 'extras-upscale'
upscaler = shared.sd_upscalers[scaler_index]
res = upscaler.scaler.upscale(image, resize, upscaler.data_path)
if mode == 1 and crop:
@@ -180,6 +184,9 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
for image, image_name in zip(imageArr, imageNameArr):
if image is None:
return outputs, "Please select an input image.", ''
+
+ shared.state.textinfo = f'Processing image {image_name}'
+
existing_pnginfo = image.info or {}
image = image.convert("RGB")
@@ -193,6 +200,10 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
else:
basename = ''
+ if opts.enable_pnginfo: # append info before save
+ image.info = existing_pnginfo
+ image.info["extras"] = info
+
if save_output:
# Add upscaler name as a suffix.
suffix = f"-{shared.sd_upscalers[extras_upscaler_1].name}" if shared.opts.use_upscaler_name_as_suffix else ""
@@ -203,10 +214,6 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
images.save_image(image, path=outpath, basename=basename, seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True,
no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None, suffix=suffix)
- if opts.enable_pnginfo:
- image.info = existing_pnginfo
- image.info["extras"] = info
-
if extras_mode != 2 or show_extras_results :
outputs.append(image)
@@ -242,6 +249,9 @@ def run_pnginfo(image):
def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format):
+ shared.state.begin()
+ shared.state.job = 'model-merge'
+
def weighted_sum(theta0, theta1, alpha):
return ((1 - alpha) * theta0) + (alpha * theta1)
@@ -263,8 +273,11 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
theta_func1, theta_func2 = theta_funcs[interp_method]
if theta_func1 and not tertiary_model_info:
+ shared.state.textinfo = "Failed: Interpolation method requires a tertiary model."
+ shared.state.end()
return ["Failed: Interpolation method requires a tertiary model."] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)]
+ shared.state.textinfo = f"Loading {secondary_model_info.filename}..."
print(f"Loading {secondary_model_info.filename}...")
theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')
@@ -281,6 +294,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
theta_1[key] = torch.zeros_like(theta_1[key])
del theta_2
+ shared.state.textinfo = f"Loading {primary_model_info.filename}..."
print(f"Loading {primary_model_info.filename}...")
theta_0 = sd_models.read_state_dict(primary_model_info.filename, map_location='cpu')
@@ -291,6 +305,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
a = theta_0[key]
b = theta_1[key]
+ shared.state.textinfo = f'Merging layer {key}'
# this enables merging an inpainting model (A) with another one (B);
# where normal model would have 4 channels, for latenst space, inpainting model would
# have another 4 channels for unmasked picture's latent space, plus one channel for mask, for a total of 9
@@ -303,8 +318,6 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
theta_0[key][:, 0:4, :, :] = theta_func2(a[:, 0:4, :, :], b, multiplier)
result_is_inpainting_model = True
else:
- assert a.shape == b.shape, f'Incompatible shapes for layer {key}: A is {a.shape}, and B is {b.shape}'
-
theta_0[key] = theta_func2(a, b, multiplier)
if save_as_half:
@@ -332,6 +345,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
output_modelname = os.path.join(ckpt_dir, filename)
+ shared.state.textinfo = f"Saving to {output_modelname}..."
print(f"Saving to {output_modelname}...")
_, extension = os.path.splitext(output_modelname)
@@ -343,4 +357,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
sd_models.list_models()
print("Checkpoint saved.")
+ shared.state.textinfo = "Checkpoint saved to " + output_modelname
+ shared.state.end()
+
return ["Checkpoint saved to " + output_modelname] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)]
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py
index 4baf4d9a..12a9de3d 100644
--- a/modules/generation_parameters_copypaste.py
+++ b/modules/generation_parameters_copypaste.py
@@ -212,11 +212,10 @@ def restore_old_hires_fix_params(res):
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
+ res['Hires resize-1'] = width
+ res['Hires resize-2'] = height
def parse_generation_parameters(x: str):
@@ -276,6 +275,10 @@ 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)
+ if "Hires resize-1" not in res:
+ res["Hires resize-1"] = 0
+ res["Hires resize-2"] = 0
+
restore_old_hires_fix_params(res)
return res
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py
index 109e8078..6a9b1398 100644
--- a/modules/hypernetworks/hypernetwork.py
+++ b/modules/hypernetworks/hypernetwork.py
@@ -402,10 +402,8 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
shared.reload_hypernetworks()
- return fn
-
-def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# images allows training previews to have infotext. Importing it at the top causes a circular import problem.
from modules import images
@@ -417,6 +415,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
shared.loaded_hypernetwork = Hypernetwork()
shared.loaded_hypernetwork.load(path)
+ shared.state.job = "train-hypernetwork"
shared.state.textinfo = "Initializing hypernetwork training..."
shared.state.job_count = steps
@@ -447,6 +446,10 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
return hypernetwork, filename
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
+
+ clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else None
+ if clip_grad:
+ clip_grad_sched = LearnRateScheduler(clip_grad_value, steps, initial_step, verbose=False)
# dataset loading may take a while, so input validations and early returns should be done before this
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
@@ -465,7 +468,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
shared.parallel_processing_allowed = False
shared.sd_model.cond_stage_model.to(devices.cpu)
shared.sd_model.first_stage_model.to(devices.cpu)
-
+
weights = hypernetwork.weights()
hypernetwork.train_mode()
@@ -524,6 +527,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
if shared.state.interrupted:
break
+ if clip_grad:
+ clip_grad_sched.step(hypernetwork.step)
+
with devices.autocast():
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
if tag_drop_out != 0 or shuffle_tags:
@@ -538,14 +544,14 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
_loss_step += loss.item()
scaler.scale(loss).backward()
+
# go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
- # print(f"grad:{weights[0].grad.detach().cpu().abs().mean().item():.7f}")
- # scaler.unscale_(optimizer)
- # print(f"grad:{weights[0].grad.detach().cpu().abs().mean().item():.15f}")
- # torch.nn.utils.clip_grad_norm_(weights, max_norm=1.0)
- # print(f"grad:{weights[0].grad.detach().cpu().abs().mean().item():.15f}")
+
+ if clip_grad:
+ clip_grad(weights, clip_grad_sched.learn_rate)
+
scaler.step(optimizer)
scaler.update()
hypernetwork.step += 1
diff --git a/modules/interrogate.py b/modules/interrogate.py
index 6f761c5a..738d8ff7 100644
--- a/modules/interrogate.py
+++ b/modules/interrogate.py
@@ -136,7 +136,8 @@ class InterrogateModels:
def interrogate(self, pil_image):
res = ""
-
+ shared.state.begin()
+ shared.state.job = 'interrogate'
try:
if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
@@ -177,5 +178,6 @@ class InterrogateModels:
res += "<error>"
self.unload()
+ shared.state.end()
return res
diff --git a/modules/processing.py b/modules/processing.py
index a172af0b..7e853287 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -76,6 +76,24 @@ def apply_overlay(image, paste_loc, index, overlays):
return image
+def txt2img_image_conditioning(sd_model, x, width, height):
+ if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
+ # Dummy zero conditioning if we're not using inpainting model.
+ # Still takes up a bit of memory, but no encoder call.
+ # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
+ return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
+
+ # The "masked-image" in this case will just be all zeros since the entire image is masked.
+ image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
+ image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
+
+ # Add the fake full 1s mask to the first dimension.
+ image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
+ image_conditioning = image_conditioning.to(x.dtype)
+
+ return image_conditioning
+
+
class StableDiffusionProcessing():
"""
The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -136,28 +154,12 @@ class StableDiffusionProcessing():
self.all_negative_prompts = None
self.all_seeds = None
self.all_subseeds = None
+ self.iteration = 0
def txt2img_image_conditioning(self, x, width=None, height=None):
- if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
- # Dummy zero conditioning if we're not using inpainting model.
- # Still takes up a bit of memory, but no encoder call.
- # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
- return x.new_zeros(x.shape[0], 5, 1, 1)
+ self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
- self.is_using_inpainting_conditioning = True
-
- height = height or self.height
- width = width or self.width
-
- # The "masked-image" in this case will just be all zeros since the entire image is masked.
- image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
- image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning))
-
- # Add the fake full 1s mask to the first dimension.
- image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
- image_conditioning = image_conditioning.to(x.dtype)
-
- return image_conditioning
+ return txt2img_image_conditioning(self.sd_model, x, width or self.width, height or self.height)
def depth2img_image_conditioning(self, source_image):
# Use the AddMiDaS helper to Format our source image to suit the MiDaS model
@@ -420,7 +422,7 @@ def fix_seed(p):
p.subseed = get_fixed_seed(p.subseed)
-def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration=0, position_in_batch=0):
+def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0):
index = position_in_batch + iteration * p.batch_size
clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers)
@@ -544,6 +546,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
state.job_count = p.n_iter
for n in range(p.n_iter):
+ p.iteration = n
+
if state.skipped:
state.skipped = False
@@ -658,12 +662,17 @@ 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, hr_scale: float = 2.0, hr_upscaler: str = None, **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, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, **kwargs):
super().__init__(**kwargs)
self.enable_hr = enable_hr
self.denoising_strength = denoising_strength
self.hr_scale = hr_scale
self.hr_upscaler = hr_upscaler
+ self.hr_second_pass_steps = hr_second_pass_steps
+ self.hr_resize_x = hr_resize_x
+ self.hr_resize_y = hr_resize_y
+ self.hr_upscale_to_x = hr_resize_x
+ self.hr_upscale_to_y = hr_resize_y
if firstphase_width != 0 or firstphase_height != 0:
print("firstphase_width/firstphase_height no longer supported; use hr_scale", file=sys.stderr)
@@ -671,14 +680,60 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
self.width = firstphase_width
self.height = firstphase_height
+ self.truncate_x = 0
+ self.truncate_y = 0
+
+
def init(self, all_prompts, all_seeds, all_subseeds):
if self.enable_hr:
- if state.job_count == -1:
- state.job_count = self.n_iter * 2
+ if self.hr_resize_x == 0 and self.hr_resize_y == 0:
+ self.extra_generation_params["Hires upscale"] = self.hr_scale
+ self.hr_upscale_to_x = int(self.width * self.hr_scale)
+ self.hr_upscale_to_y = int(self.height * self.hr_scale)
else:
+ self.extra_generation_params["Hires resize"] = f"{self.hr_resize_x}x{self.hr_resize_y}"
+
+ if self.hr_resize_y == 0:
+ self.hr_upscale_to_x = self.hr_resize_x
+ self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
+ elif self.hr_resize_x == 0:
+ self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
+ self.hr_upscale_to_y = self.hr_resize_y
+ else:
+ target_w = self.hr_resize_x
+ target_h = self.hr_resize_y
+ src_ratio = self.width / self.height
+ dst_ratio = self.hr_resize_x / self.hr_resize_y
+
+ if src_ratio < dst_ratio:
+ self.hr_upscale_to_x = self.hr_resize_x
+ self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
+ else:
+ self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
+ self.hr_upscale_to_y = self.hr_resize_y
+
+ self.truncate_x = (self.hr_upscale_to_x - target_w) // opt_f
+ self.truncate_y = (self.hr_upscale_to_y - target_h) // opt_f
+
+ # special case: the user has chosen to do nothing
+ if self.hr_upscale_to_x == self.width and self.hr_upscale_to_y == self.height:
+ self.enable_hr = False
+ self.denoising_strength = None
+ self.extra_generation_params.pop("Hires upscale", None)
+ self.extra_generation_params.pop("Hires resize", None)
+ return
+
+ if not state.processing_has_refined_job_count:
+ if state.job_count == -1:
+ state.job_count = self.n_iter
+
+ shared.total_tqdm.updateTotal((self.steps + (self.hr_second_pass_steps or self.steps)) * state.job_count)
state.job_count = state.job_count * 2
+ state.processing_has_refined_job_count = True
+
+ if self.hr_second_pass_steps:
+ self.extra_generation_params["Hires steps"] = self.hr_second_pass_steps
- 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
@@ -695,8 +750,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
if not self.enable_hr:
return samples
- target_width = int(self.width * self.hr_scale)
- target_height = int(self.height * self.hr_scale)
+ target_width = self.hr_upscale_to_x
+ target_height = self.hr_upscale_to_y
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"""
@@ -705,15 +760,16 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
return
if not isinstance(image, Image.Image):
- image = sd_samplers.sample_to_image(image, index)
+ image = sd_samplers.sample_to_image(image, index, approximation=0)
- images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
+ info = create_infotext(self, self.all_prompts, self.all_seeds, self.all_subseeds, [], iteration=self.iteration, position_in_batch=index)
+ images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, info=info, suffix="-before-highres-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=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode)
+ samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode["mode"], antialias=latent_scale_mode["antialias"])
# Avoid making the inpainting conditioning unless necessary as
# this does need some extra compute to decode / encode the image again.
@@ -750,13 +806,15 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
+ samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2]
+
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
devices.torch_gc()
- samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=image_conditioning)
+ samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
return samples
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py
index 55a684cc..ef25dadb 100644
--- a/modules/sd_hijack.py
+++ b/modules/sd_hijack.py
@@ -33,25 +33,34 @@ def apply_optimizations():
ldm.modules.diffusionmodules.model.nonlinearity = silu
ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
+
+ optimization_method = None
if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
print("Applying xformers cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
+ optimization_method = 'xformers'
elif cmd_opts.opt_sub_quad_attention:
print("Applying sub-quadratic cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.sub_quad_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.sub_quad_attnblock_forward
+ optimization_method = 'sub-quadratic'
elif cmd_opts.opt_split_attention_v1:
print("Applying v1 cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
+ optimization_method = 'V1'
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention_invokeai or not torch.cuda.is_available()):
print("Applying cross attention optimization (InvokeAI).")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_invokeAI
+ optimization_method = 'InvokeAI'
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
print("Applying cross attention optimization (Doggettx).")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
+ optimization_method = 'Doggettx'
+
+ return optimization_method
def undo_optimizations():
@@ -72,6 +81,7 @@ class StableDiffusionModelHijack:
layers = None
circular_enabled = False
clip = None
+ optimization_method = None
embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase(cmd_opts.embeddings_dir)
@@ -91,7 +101,7 @@ class StableDiffusionModelHijack:
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()
+ self.optimization_method = apply_optimizations()
self.clip = m.cond_stage_model
diff --git a/modules/sd_hijack_inpainting.py b/modules/sd_hijack_inpainting.py
index 3c214a35..31d2c898 100644
--- a/modules/sd_hijack_inpainting.py
+++ b/modules/sd_hijack_inpainting.py
@@ -97,8 +97,11 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F
def should_hijack_inpainting(checkpoint_info):
+ from modules import sd_models
+
ckpt_basename = os.path.basename(checkpoint_info.filename).lower()
- cfg_basename = os.path.basename(checkpoint_info.config).lower()
+ cfg_basename = os.path.basename(sd_models.find_checkpoint_config(checkpoint_info)).lower()
+
return "inpainting" in ckpt_basename and not "inpainting" in cfg_basename
diff --git a/modules/sd_models.py b/modules/sd_models.py
index b98b05fc..76a89e88 100644
--- a/modules/sd_models.py
+++ b/modules/sd_models.py
@@ -20,7 +20,7 @@ from modules.sd_hijack_inpainting import do_inpainting_hijack, should_hijack_inp
model_dir = "Stable-diffusion"
model_path = os.path.abspath(os.path.join(models_path, model_dir))
-CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash', 'model_name', 'config'])
+CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash', 'model_name'])
checkpoints_list = {}
checkpoints_loaded = collections.OrderedDict()
@@ -48,6 +48,14 @@ def checkpoint_tiles():
return sorted([x.title for x in checkpoints_list.values()], key = alphanumeric_key)
+def find_checkpoint_config(info):
+ config = os.path.splitext(info.filename)[0] + ".yaml"
+ if os.path.exists(config):
+ return config
+
+ return shared.cmd_opts.config
+
+
def list_models():
checkpoints_list.clear()
model_list = modelloader.load_models(model_path=model_path, command_path=shared.cmd_opts.ckpt_dir, ext_filter=[".ckpt", ".safetensors"])
@@ -73,7 +81,7 @@ def list_models():
if os.path.exists(cmd_ckpt):
h = model_hash(cmd_ckpt)
title, short_model_name = modeltitle(cmd_ckpt, h)
- checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h, short_model_name, shared.cmd_opts.config)
+ checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h, short_model_name)
shared.opts.data['sd_model_checkpoint'] = title
elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file: