sd-webui/stable-diffusion-webui
1
1
Fork 0
mirror of https://github.com/sd-webui/stable-diffusion-webui.git synced 2024-12-15 07:12:58 +03:00
Code Issues Projects Releases Wiki Activity

Corrected breaking issues introduced in #1136 to txt2img and

Browse Source 
made state variables consistent with img2img.

Fixed a bug where switching models after running would not reload
the used model.
This commit is contained in:
protoplm 2022-09-14 19:59:53 -04:00
parent 178e62292e
commit 4f7adcaf42
2 changed files with 87 additions and 87 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
scripts/sd_utils.py
View File

@ -164,7 +164,7 @@ def load_models(continue_prev_run = False, use_GFPGAN=False, use_RealESRGAN=Fals
del st.session_state["RealESRGAN"] del st.session_state["RealESRGAN"]
if "model" in st.session_state: if "model" in st.session_state:
if "model" in st.session_state and st.session_state["custom_model"] == custom_model: if "model" in st.session_state and st.session_state["loaded_model"] == custom_model:
# TODO: check if the optimized mode was changed? # TODO: check if the optimized mode was changed?
print("Model already loaded") print("Model already loaded")
@ -188,6 +188,7 @@ def load_models(continue_prev_run = False, use_GFPGAN=False, use_RealESRGAN=Fals
st.session_state.model = model st.session_state.model = model
st.session_state.modelCS = modelCS st.session_state.modelCS = modelCS
st.session_state.modelFS = modelFS st.session_state.modelFS = modelFS
st.session_state.loaded_model = custom_model
print("Model loaded.") print("Model loaded.")
@ -882,26 +883,21 @@ def slerp(device, t, v0:torch.Tensor, v1:torch.Tensor, DOT_THRESHOLD=0.9995):
return v2 return v2
# #
def optimize_update_preview_frequency(current_chunk_speed, previous_chunk_speed_list, update_preview_frequency, update_preview_frequency_list): def optimize_update_preview_frequency(current_chunk_speed, previous_chunk_speed, update_preview_frequency):
"""Find the optimal update_preview_frequency value maximizing """Find the optimal update_preview_frequency value maximizing
performance while minimizing the time between updates.""" performance while minimizing the time between updates."""
from statistics import mean if current_chunk_speed >= previous_chunk_speed:
previous_chunk_avg_speed = mean(previous_chunk_speed_list)
previous_chunk_speed_list.append(current_chunk_speed)
current_chunk_avg_speed = mean(previous_chunk_speed_list)
if current_chunk_avg_speed >= previous_chunk_avg_speed:
#print(f"{current_chunk_speed} >= {previous_chunk_speed}") #print(f"{current_chunk_speed} >= {previous_chunk_speed}")
update_preview_frequency_list.append(update_preview_frequency + 1) update_preview_frequency +=1
previous_chunk_speed = current_chunk_speed
else: else:
#print(f"{current_chunk_speed} <= {previous_chunk_speed}") #print(f"{current_chunk_speed} <= {previous_chunk_speed}")
update_preview_frequency_list.append(update_preview_frequency - 1) update_preview_frequency -=1
previous_chunk_speed = current_chunk_speed
update_preview_frequency = round(mean(update_preview_frequency_list))
return current_chunk_speed, previous_chunk_speed, update_preview_frequency
return current_chunk_speed, previous_chunk_speed_list, update_preview_frequency, update_preview_frequency_list
def get_font(fontsize): def get_font(fontsize):

148
scripts/txt2img.py
View File

@ -30,11 +30,11 @@ except:
pass pass
class plugin_info(): class plugin_info():
plugname = "txt2img" plugname = "txt2img"
description = "Text to Image" description = "Text to Image"
isTab = True isTab = True
displayPriority = 1 displayPriority = 1
if os.path.exists(os.path.join(st.session_state['defaults'].general.GFPGAN_dir, "experiments", "pretrained_models", "GFPGANv1.3.pth")): if os.path.exists(os.path.join(st.session_state['defaults'].general.GFPGAN_dir, "experiments", "pretrained_models", "GFPGANv1.3.pth")):
GFPGAN_available = True GFPGAN_available = True
@ -48,12 +48,12 @@ else:
# #
def txt2img(prompt: str, ddim_steps: int, sampler_name: str, realesrgan_model_name: str, def txt2img(prompt: str, ddim_steps: int, sampler_name: str, realesrgan_model_name: str,
n_iter: int, batch_size: int, cfg_scale: float, seed: Union[int, str, None], n_iter: int, batch_size: int, cfg_scale: float, seed: Union[int, str, None],
height: int, width: int, separate_prompts:bool = False, normalize_prompt_weights:bool = True, height: int, width: int, separate_prompts:bool = False, normalize_prompt_weights:bool = True,
save_individual_images: bool = True, save_grid: bool = True, group_by_prompt: bool = True, save_individual_images: bool = True, save_grid: bool = True, group_by_prompt: bool = True,
save_as_jpg: bool = True, use_GFPGAN: bool = True, use_RealESRGAN: bool = True, save_as_jpg: bool = True, use_GFPGAN: bool = True, use_RealESRGAN: bool = True,
RealESRGAN_model: str = "RealESRGAN_x4plus_anime_6B", fp = None, variant_amount: float = None, RealESRGAN_model: str = "RealESRGAN_x4plus_anime_6B", fp = None, variant_amount: float = None,
variant_seed: int = None, ddim_eta:float = 0.0, write_info_files:bool = True): variant_seed: int = None, ddim_eta:float = 0.0, write_info_files:bool = True):
outpath = st.session_state['defaults'].general.outdir_txt2img or st.session_state['defaults'].general.outdir or "outputs/txt2img-samples" outpath = st.session_state['defaults'].general.outdir_txt2img or st.session_state['defaults'].general.outdir or "outputs/txt2img-samples"
@ -93,40 +93,40 @@ def txt2img(prompt: str, ddim_steps: int, sampler_name: str, realesrgan_model_na
def sample(init_data, x, conditioning, unconditional_conditioning, sampler_name): def sample(init_data, x, conditioning, unconditional_conditioning, sampler_name):
samples_ddim, _ = sampler.sample(S=ddim_steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=cfg_scale, samples_ddim, _ = sampler.sample(S=ddim_steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=cfg_scale,
unconditional_conditioning=unconditional_conditioning, eta=ddim_eta, x_T=x, img_callback=generation_callback, unconditional_conditioning=unconditional_conditioning, eta=ddim_eta, x_T=x, img_callback=generation_callback,
log_every_t=int(st.session_state['defaults'].general.update_preview_frequency)) log_every_t=int(st.session_state['defaults'].general.update_preview_frequency))
return samples_ddim return samples_ddim
#try: #try:
output_images, seed, info, stats = process_images( output_images, seed, info, stats = process_images(
outpath=outpath, outpath=outpath,
func_init=init, func_init=init,
func_sample=sample, func_sample=sample,
prompt=prompt, prompt=prompt,
seed=seed, seed=seed,
sampler_name=sampler_name, sampler_name=sampler_name,
save_grid=save_grid, save_grid=save_grid,
batch_size=batch_size, batch_size=batch_size,
n_iter=n_iter, n_iter=n_iter,
steps=ddim_steps, steps=ddim_steps,
cfg_scale=cfg_scale, cfg_scale=cfg_scale,
width=width, width=width,
height=height, height=height,
prompt_matrix=separate_prompts, prompt_matrix=separate_prompts,
use_GFPGAN=use_GFPGAN, use_GFPGAN=st.session_state["use_GFPGAN"],
use_RealESRGAN=use_RealESRGAN, use_RealESRGAN=st.session_state["use_RealESRGAN"],
realesrgan_model_name=realesrgan_model_name, realesrgan_model_name=realesrgan_model_name,
fp=fp, fp=fp,
ddim_eta=ddim_eta, ddim_eta=ddim_eta,
normalize_prompt_weights=normalize_prompt_weights, normalize_prompt_weights=normalize_prompt_weights,
save_individual_images=save_individual_images, save_individual_images=save_individual_images,
sort_samples=group_by_prompt, sort_samples=group_by_prompt,
write_info_files=write_info_files, write_info_files=write_info_files,
jpg_sample=save_as_jpg, jpg_sample=save_as_jpg,
variant_amount=variant_amount, variant_amount=variant_amount,
variant_seed=variant_seed, variant_seed=variant_seed,
) )
del sampler del sampler
@ -176,16 +176,16 @@ def layout():
help="How many images are at once in a batch.\ help="How many images are at once in a batch.\
It increases the VRAM usage a lot but if you have enough VRAM it can reduce the time it takes to finish generation as more images are generated at once.\ It increases the VRAM usage a lot but if you have enough VRAM it can reduce the time it takes to finish generation as more images are generated at once.\
Default: 1") Default: 1")
with st.expander("Preview Settings"): with st.expander("Preview Settings"):
st.session_state["update_preview"] = st.checkbox("Update Image Preview", value=st.session_state['defaults'].txt2img.update_preview, st.session_state["update_preview"] = st.checkbox("Update Image Preview", value=st.session_state['defaults'].txt2img.update_preview,
help="If enabled the image preview will be updated during the generation instead of at the end. \ help="If enabled the image preview will be updated during the generation instead of at the end. \
You can use the Update Preview \Frequency option bellow to customize how frequent it's updated. \ You can use the Update Preview \Frequency option bellow to customize how frequent it's updated. \
By default this is enabled and the frequency is set to 1 step.") By default this is enabled and the frequency is set to 1 step.")
st.session_state["update_preview_frequency"] = st.text_input("Update Image Preview Frequency", value=st.session_state['defaults'].txt2img.update_preview_frequency, st.session_state["update_preview_frequency"] = st.text_input("Update Image Preview Frequency", value=st.session_state['defaults'].txt2img.update_preview_frequency,
help="Frequency in steps at which the the preview image is updated. By default the frequency \ help="Frequency in steps at which the the preview image is updated. By default the frequency \
is set to 1 step.") is set to 1 step.")
with col2: with col2:
preview_tab, gallery_tab = st.tabs(["Preview", "Gallery"]) preview_tab, gallery_tab = st.tabs(["Preview", "Gallery"])
@ -210,13 +210,13 @@ def layout():
with col3: with col3:
# If we have custom models available on the "models/custom" # If we have custom models available on the "models/custom"
#folder then we show a menu to select which model we want to use, otherwise we use the main model for SD #folder then we show a menu to select which model we want to use, otherwise we use the main model for SD
#if CustomModel_available: if st.session_state["CustomModel_available"]:
custom_model = st.selectbox("Custom Model:", st.session_state['defaults'].txt2vid.custom_models_list, st.session_state["custom_model"] = st.selectbox("Custom Model:", st.session_state["custom_models"],
index=st.session_state['defaults'].txt2vid.custom_models_list.index(st.session_state['defaults'].txt2vid.default_model), index=st.session_state["custom_models"].index(st.session_state['defaults'].general.default_model),
help="Select the model you want to use. This option is only available if you have custom models \ help="Select the model you want to use. This option is only available if you have custom models \
on your 'models/custom' folder. The model name that will be shown here is the same as the name\ on your 'models/custom' folder. The model name that will be shown here is the same as the name\
the file for the model has on said folder, it is recommended to give the .ckpt file a name that \ the file for the model has on said folder, it is recommended to give the .ckpt file a name that \
will make it easier for you to distinguish it from other models. Default: Stable Diffusion v1.4") will make it easier for you to distinguish it from other models. Default: Stable Diffusion v1.4")
st.session_state.sampling_steps = st.slider("Sampling Steps", value=st.session_state['defaults'].txt2img.sampling_steps, min_value=1, max_value=250) st.session_state.sampling_steps = st.slider("Sampling Steps", value=st.session_state['defaults'].txt2img.sampling_steps, min_value=1, max_value=250)
@ -242,17 +242,20 @@ def layout():
write_info_files = st.checkbox("Write Info file", value=True, help="Save a file next to the image with informartion about the generation.") write_info_files = st.checkbox("Write Info file", value=True, help="Save a file next to the image with informartion about the generation.")
save_as_jpg = st.checkbox("Save samples as jpg", value=False, help="Saves the images as jpg instead of png.") save_as_jpg = st.checkbox("Save samples as jpg", value=False, help="Saves the images as jpg instead of png.")
if GFPGAN_available: if st.session_state["GFPGAN_available"]:
use_GFPGAN = st.checkbox("Use GFPGAN", value=st.session_state['defaults'].txt2img.use_GFPGAN, help="Uses the GFPGAN model to improve faces after the generation. This greatly improve the quality and consistency of faces but uses extra VRAM. Disable if you need the extra VRAM.") st.session_state["use_GFPGAN"] = st.checkbox("Use GFPGAN", value=st.session_state['defaults'].txt2img.use_GFPGAN, help="Uses the GFPGAN model to improve faces after the generation.\
This greatly improve the quality and consistency of faces but uses extra VRAM. Disable if you need the extra VRAM.")
else: else:
use_GFPGAN = False st.session_state["use_GFPGAN"] = False
if RealESRGAN_available: if st.session_state["RealESRGAN_available"]:
use_RealESRGAN = st.checkbox("Use RealESRGAN", value=st.session_state['defaults'].txt2img.use_RealESRGAN, help="Uses the RealESRGAN model to upscale the images after the generation. This greatly improve the quality and lets you have high resolution images but uses extra VRAM. Disable if you need the extra VRAM.") st.session_state["use_RealESRGAN"] = st.checkbox("Use RealESRGAN", value=st.session_state['defaults'].txt2img.use_RealESRGAN,
RealESRGAN_model = st.selectbox("RealESRGAN model", ["RealESRGAN_x4plus", "RealESRGAN_x4plus_anime_6B"], index=0) help="Uses the RealESRGAN model to upscale the images after the generation.\
This greatly improve the quality and lets you have high resolution images but uses extra VRAM. Disable if you need the extra VRAM.")
st.session_state["RealESRGAN_model"] = st.selectbox("RealESRGAN model", ["RealESRGAN_x4plus", "RealESRGAN_x4plus_anime_6B"], index=0)
else: else:
use_RealESRGAN = False st.session_state["use_RealESRGAN"] = False
RealESRGAN_model = "RealESRGAN_x4plus" st.session_state["RealESRGAN_model"] = "RealESRGAN_x4plus"
variant_amount = st.slider("Variant Amount:", value=st.session_state['defaults'].txt2img.variant_amount, min_value=0.0, max_value=1.0, step=0.01) variant_amount = st.slider("Variant Amount:", value=st.session_state['defaults'].txt2img.variant_amount, min_value=0.0, max_value=1.0, step=0.01)
variant_seed = st.text_input("Variant Seed:", value=st.session_state['defaults'].txt2img.seed, help="The seed to use when generating a variant, if left blank a random seed will be generated.") variant_seed = st.text_input("Variant Seed:", value=st.session_state['defaults'].txt2img.seed, help="The seed to use when generating a variant, if left blank a random seed will be generated.")
@ -260,14 +263,15 @@ def layout():
if generate_button: if generate_button:
#print("Loading models") #print("Loading models")
# load the models when we hit the generate button for the first time, it wont be loaded after that so dont worry. # load the models when we hit the generate button for the first time, it wont be loaded after that so dont worry.
load_models(False, use_GFPGAN, use_RealESRGAN, RealESRGAN_model) load_models(False, st.session_state["use_GFPGAN"], st.session_state["use_RealESRGAN"], st.session_state["RealESRGAN_model"], st.session_state["CustomModel_available"],
st.session_state["custom_model"])
try: try:
output_images, seeds, info, stats = txt2img(prompt, st.session_state.sampling_steps, sampler_name, RealESRGAN_model, batch_count, batch_size, output_images, seeds, info, stats = txt2img(prompt, st.session_state.sampling_steps, sampler_name, st.session_state["RealESRGAN_model"], batch_count, batch_size,
cfg_scale, seed, height, width, separate_prompts, normalize_prompt_weights, save_individual_images, cfg_scale, seed, height, width, separate_prompts, normalize_prompt_weights, save_individual_images,
save_grid, group_by_prompt, save_as_jpg, use_GFPGAN, use_RealESRGAN, RealESRGAN_model, fp=st.session_state.defaults.general.fp, save_grid, group_by_prompt, save_as_jpg, st.session_state["use_GFPGAN"], st.session_state["use_RealESRGAN"], st.session_state["RealESRGAN_model"],
variant_amount=variant_amount, variant_seed=variant_seed, write_info_files=write_info_files) fp=st.session_state.defaults.general.fp, variant_amount=variant_amount, variant_seed=variant_seed, write_info_files=write_info_files)
message.success('Render Complete: ' + info + '; Stats: ' + stats, icon="✅") message.success('Render Complete: ' + info + '; Stats: ' + stats, icon="✅")
@ -319,11 +323,11 @@ def layout():
#on import run init #on import run init
def createHTMLGallery(images,info): def createHTMLGallery(images,info):
html3 = """ html3 = """
<div class="gallery-history" style=" <div class="gallery-history" style="
display: flex; display: flex;
flex-wrap: wrap; flex-wrap: wrap;
align-items: flex-start;"> align-items: flex-start;">
""" """
mkdwn_array = [] mkdwn_array = []
for i in images: for i in images:
try: try:
@ -352,7 +356,7 @@ def createHTMLGallery(images,info):
#mkdwn = f"""<img src="{img_str}" alt="Image" with="200" height="200" />""" #mkdwn = f"""<img src="{img_str}" alt="Image" with="200" height="200" />"""
mkdwn = f'''<div class="gallery" style="margin: 3px;" > mkdwn = f'''<div class="gallery" style="margin: 3px;" >
<a href="{img_str}"> <a href="{img_str}">
<img src="{img_str}" alt="Image" width="{width}" height="{height}"> <img src="{img_str}" alt="Image" width="{width}" height="{height}">
</a> </a>
<div class="desc" style="text-align: center; opacity: 40%;">{seed}</div> <div class="desc" style="text-align: center; opacity: 40%;">{seed}</div>
</div> </div>