mirror of
https://github.com/vladmandic/automatic
synced 2026-09-19 17:24:32 +02:00
multiple cleanups
This commit is contained in:
Vladimir Mandic
+2
-2
@@ -255,7 +255,7 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None, output_type
|
||||
src_w = width if ratio > src_ratio else im.width * height // im.height
|
||||
src_h = height if ratio <= src_ratio else im.height * width // im.width
|
||||
resized = resize(im, src_w, src_h)
|
||||
res = Image.new("RGB", (width, height))
|
||||
res = Image.new(im.mode, (width, height))
|
||||
res.paste(resized, box=(width // 2 - src_w // 2, height // 2 - src_h // 2))
|
||||
else:
|
||||
ratio = width / height
|
||||
@@ -263,7 +263,7 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None, output_type
|
||||
src_w = width if ratio < src_ratio else im.width * height // im.height
|
||||
src_h = height if ratio >= src_ratio else im.height * width // im.width
|
||||
resized = resize(im, src_w, src_h)
|
||||
res = Image.new("RGB", (width, height))
|
||||
res = Image.new(im.mode, (width, height))
|
||||
res.paste(resized, box=(width // 2 - src_w // 2, height // 2 - src_h // 2))
|
||||
if ratio < src_ratio:
|
||||
fill_height = height // 2 - src_h // 2
|
||||
|
||||
@@ -686,6 +686,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
|
||||
p.override_settings.pop(k, None)
|
||||
for k in p.override_settings.keys():
|
||||
stored_opts[k] = shared.opts.data.get(k, None) or shared.opts.data_labels[k].default
|
||||
res = None
|
||||
try:
|
||||
# if no checkpoint override or the override checkpoint can't be found, remove override entry and load opts checkpoint
|
||||
if p.override_settings.get('sd_model_checkpoint', None) is not None and modules.sd_models.checkpoint_aliases.get(p.override_settings.get('sd_model_checkpoint')) is None:
|
||||
@@ -1210,7 +1211,6 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
|
||||
def init(self, all_prompts, all_seeds, all_subseeds):
|
||||
if shared.backend == shared.Backend.DIFFUSERS and self.image_mask is not None:
|
||||
shared.sd_model = modules.sd_models.set_diffuser_pipe(self.sd_model, modules.sd_models.DiffusersTaskType.INPAINTING)
|
||||
# self.sd_model.dtype = self.sd_model.unet.dtype
|
||||
elif shared.backend == shared.Backend.DIFFUSERS and self.image_mask is None:
|
||||
shared.sd_model = modules.sd_models.set_diffuser_pipe(self.sd_model, modules.sd_models.DiffusersTaskType.IMAGE_2_IMAGE)
|
||||
|
||||
@@ -1225,6 +1225,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
|
||||
else:
|
||||
self.ops.append('img2img')
|
||||
crop_region = None
|
||||
|
||||
image_mask = self.image_mask
|
||||
if image_mask is not None:
|
||||
if type(image_mask) == list:
|
||||
@@ -1250,6 +1251,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
|
||||
self.mask_for_overlay = Image.fromarray(np_mask)
|
||||
self.overlay_images = []
|
||||
latent_mask = self.latent_mask if self.latent_mask is not None else image_mask
|
||||
|
||||
add_color_corrections = shared.opts.img2img_color_correction and self.color_corrections is None
|
||||
if add_color_corrections:
|
||||
self.color_corrections = []
|
||||
@@ -1280,14 +1282,12 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
|
||||
if crop_region is not None:
|
||||
image = image.crop(crop_region)
|
||||
image = images.resize_image(3, image, self.width, self.height)
|
||||
if shared.backend == shared.Backend.DIFFUSERS:
|
||||
unprocessed.append(image)
|
||||
self.init_images = [image] # assign early for diffusers
|
||||
if image_mask is not None:
|
||||
if self.inpainting_fill != 1:
|
||||
image = modules.masking.fill(image, latent_mask)
|
||||
if image_mask is not None and self.inpainting_fill != 1:
|
||||
image = modules.masking.fill(image, latent_mask)
|
||||
if add_color_corrections:
|
||||
self.color_corrections.append(setup_color_correction(image))
|
||||
if shared.backend == shared.Backend.DIFFUSERS:
|
||||
unprocessed.append(image) # assign early for diffusers
|
||||
image = np.array(image).astype(np.float32) / 255.0
|
||||
image = np.moveaxis(image, 2, 0)
|
||||
imgs.append(image)
|
||||
@@ -1304,8 +1304,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
|
||||
else:
|
||||
raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
|
||||
if shared.backend == shared.Backend.DIFFUSERS:
|
||||
# we've already set self.init_images and self.mask and we dont need any more processing
|
||||
return
|
||||
return # we've already set self.init_images and self.mask and we dont need any more processing
|
||||
|
||||
image = torch.from_numpy(batch_images)
|
||||
image = 2. * image - 1.
|
||||
|
||||
@@ -31,10 +31,10 @@ def process_diffusers(p: StableDiffusionProcessing, seeds, prompts, negative_pro
|
||||
p.height = tgt_height
|
||||
p.width = tgt_width
|
||||
hypertile_set(p)
|
||||
if getattr(p, 'mask', None) is not None:
|
||||
p.mask = images.resize_image(1, p.mask, tgt_width, tgt_height, upscaler_name=None)
|
||||
if getattr(p, 'mask_for_overlay', None) is not None:
|
||||
p.mask_for_overlay = images.resize_image(1, p.mask_for_overlay, tgt_width, tgt_height, upscaler_name=None)
|
||||
if getattr(p, 'mask', None) is not None and p.mask.size != (tgt_width, tgt_height):
|
||||
p.mask = images.resize_image(1, p.mask, tgt_width, tgt_height, upscaler_name=None)
|
||||
if getattr(p, 'mask_for_overlay', None) is not None and p.mask_for_overlay.size != (tgt_width, tgt_height):
|
||||
p.mask_for_overlay = images.resize_image(1, p.mask_for_overlay, tgt_width, tgt_height, upscaler_name=None)
|
||||
|
||||
def hires_resize(latents): # input=latents output=pil
|
||||
latent_upscaler = shared.latent_upscale_modes.get(p.hr_upscaler, None)
|
||||
@@ -215,7 +215,30 @@ def process_diffusers(p: StableDiffusionProcessing, seeds, prompts, negative_pro
|
||||
p.mask = TF.to_pil_image(torch.ones_like(TF.to_tensor(p.init_images[0]))).convert("L")
|
||||
width = 8 * math.ceil(p.init_images[0].width / 8)
|
||||
height = 8 * math.ceil(p.init_images[0].height / 8)
|
||||
|
||||
# option-1: use images as inputs
|
||||
task_args = {"image": p.init_images, "mask_image": p.mask, "strength": p.denoising_strength, "height": height, "width": width}
|
||||
|
||||
""" # option-2: preprocess images into latents using diffusers
|
||||
vae_scale_factor = 2 ** (len(model.vae.config.block_out_channels) - 1)
|
||||
image_processor = diffusers.image_processor.VaeImageProcessor(vae_scale_factor=vae_scale_factor)
|
||||
mask_processor = diffusers.image_processor.VaeImageProcessor(vae_scale_factor=vae_scale_factor, do_normalize=False, do_binarize=True, do_convert_grayscale=True)
|
||||
init_image = image_processor.preprocess(p.init_images[0], width=width, height=height)
|
||||
mask_image = mask_processor.preprocess(p.mask, width=width, height=height)
|
||||
task_args = {"image": p.init_images, "mask_image": p.mask, "strength": p.denoising_strength, "height": height, "width": width}
|
||||
"""
|
||||
|
||||
""" # option-2: manually assemble masked image latents
|
||||
masked_image_latents = []
|
||||
mask_image = TF.to_tensor(p.mask)
|
||||
for init_image in p.init_images:
|
||||
init_image = TF.to_tensor(p.init_images[0])
|
||||
masked_image = init_image * (mask_image > 0.5)
|
||||
masked_image_latents.append(torch.cat([masked_image, mask_image], dim=0))
|
||||
masked_image_latents = torch.stack(masked_image_latents, dim=0).to(shared.device)
|
||||
task_args = {"image": p.init_images, "mask_image": mask_image, "masked_image_latents": masked_image_latents, "strength": p.denoising_strength, "height": height, "width": width}
|
||||
"""
|
||||
|
||||
if model.__class__.__name__ == 'LatentConsistencyModelPipeline' and hasattr(p, 'init_images') and len(p.init_images) > 0:
|
||||
init_latents = [vae_encode(image, model=shared.sd_model, full_quality=p.full_quality).squeeze(dim=0) for image in p.init_images]
|
||||
init_latent = torch.stack(init_latents, dim=0).to(shared.device)
|
||||
@@ -307,6 +330,8 @@ def process_diffusers(p: StableDiffusionProcessing, seeds, prompts, negative_pro
|
||||
clean['image'] = type(clean['image'])
|
||||
if 'mask_image' in clean:
|
||||
clean['mask_image'] = type(clean['mask_image'])
|
||||
if 'masked_image_latents' in clean:
|
||||
clean['masked_image_latents'] = type(clean['masked_image_latents'])
|
||||
if 'prompt' in clean:
|
||||
clean['prompt'] = len(clean['prompt'])
|
||||
if 'negative_prompt' in clean:
|
||||
@@ -408,6 +433,9 @@ def process_diffusers(p: StableDiffusionProcessing, seeds, prompts, negative_pro
|
||||
shared.log.debug(f'Steps: type=refiner input={p.refiner_steps} output={steps} start={p.refiner_start} denoise={p.denoising_strength}')
|
||||
return max(2, int(steps))
|
||||
|
||||
a = 1
|
||||
a = (a * 2)
|
||||
|
||||
# pipeline type is set earlier in processing, but check for sanity
|
||||
if sd_models.get_diffusers_task(shared.sd_model) != sd_models.DiffusersTaskType.TEXT_2_IMAGE and len(getattr(p, 'init_images' ,[])) == 0:
|
||||
shared.sd_model = sd_models.set_diffuser_pipe(shared.sd_model, sd_models.DiffusersTaskType.TEXT_2_IMAGE) # reset pipeline
|
||||
|
||||
+4
-4
@@ -421,7 +421,7 @@ def create_ui(startup_timer = None):
|
||||
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.1, label='CFG scale', value=6.0, elem_id="txt2img_cfg_scale")
|
||||
clip_skip = gr.Slider(label='CLIP skip', value=1, minimum=1, maximum=14, step=1, elem_id='txt2img_clip_skip', interactive=True)
|
||||
with FormRow():
|
||||
image_cfg_scale = gr.Slider(minimum=1.1, maximum=30.0, step=0.1, label='Secondary CFG scale', value=6.0, elem_id="txt2img_image_cfg_scale")
|
||||
image_cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.1, label='Secondary CFG scale', value=6.0, elem_id="txt2img_image_cfg_scale")
|
||||
diffusers_guidance_rescale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Guidance rescale', value=0.7, elem_id="txt2img_image_cfg_rescale")
|
||||
with FormRow():
|
||||
full_quality = gr.Checkbox(label='Full quality', value=True, elem_id="txt2img_full_quality")
|
||||
@@ -711,8 +711,8 @@ def create_ui(startup_timer = None):
|
||||
|
||||
with gr.Accordion(open=False, label="Advanced", elem_classes=["small-accordion"], elem_id="img2img_advanced_group"):
|
||||
with FormRow():
|
||||
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG scale', value=6.0, elem_id="img2img_cfg_scale")
|
||||
image_cfg_scale = gr.Slider(minimum=0, maximum=30.0, step=0.05, label='Image CFG scale', value=1.5, elem_id="img2img_image_cfg_scale")
|
||||
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.1, label='CFG scale', value=6.0, elem_id="img2img_cfg_scale")
|
||||
image_cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.15, label='Image CFG scale', value=1.5, elem_id="img2img_image_cfg_scale")
|
||||
with FormRow():
|
||||
clip_skip = gr.Slider(label='CLIP skip', value=1, minimum=1, maximum=4, step=1, elem_id='img2img_clip_skip', interactive=True)
|
||||
diffusers_guidance_rescale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Guidance rescale', value=0.7, elem_id="txt2img_image_cfg_rescale")
|
||||
@@ -729,7 +729,7 @@ def create_ui(startup_timer = None):
|
||||
with gr.Column():
|
||||
inpainting_mask_invert = gr.Radio(label='Mask mode', choices=['Inpaint masked', 'Inpaint not masked'], value='Inpaint masked', type="index", elem_id="img2img_mask_mode")
|
||||
with gr.Column():
|
||||
inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='original', type="index", elem_id="img2img_inpainting_fill")
|
||||
inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'noise', 'nothing'], value='original', type="index", elem_id="img2img_inpainting_fill")
|
||||
with FormRow():
|
||||
with gr.Column():
|
||||
inpaint_full_res = gr.Radio(label="Inpaint area", choices=["Whole picture", "Only masked"], type="index", value="Whole picture", elem_id="img2img_inpaint_full_res")
|
||||
|
||||
+2
-2
@@ -53,14 +53,14 @@ opencv-python-headless==4.7.0.72
|
||||
diffusers==0.23.0
|
||||
einops==0.4.1
|
||||
gradio==3.43.2
|
||||
huggingface_hub==0.18.0
|
||||
huggingface_hub==0.19.2
|
||||
numexpr==2.8.4
|
||||
numpy==1.24.4
|
||||
numba==0.57.1
|
||||
pandas==1.5.3
|
||||
protobuf==3.20.3
|
||||
pytorch_lightning==1.9.4
|
||||
transformers==4.34.1
|
||||
transformers==4.35.1
|
||||
tomesd==0.1.3
|
||||
urllib3==1.26.15
|
||||
Pillow==9.5.0
|
||||
|
||||
+20
-20
@@ -236,29 +236,29 @@ axis_options = [
|
||||
AxisOption("Clip skip", int, apply_clip_skip),
|
||||
AxisOption("Denoising strength", float, apply_field("denoising_strength")),
|
||||
AxisOption("Prompt order", str_permutations, apply_order, fmt=format_value_join_list),
|
||||
AxisOption("Model dictionary", str, apply_dict, fmt=format_value, cost=1.0, choices=lambda: ['None'] + list(sd_models.checkpoints_list)),
|
||||
AxisOptionImg2Img("Image mask weight", float, apply_field("inpainting_mask_weight")),
|
||||
AxisOption("[Postprocess] Upscaler", str, apply_upscaler, choices=lambda: [x.name for x in shared.sd_upscalers][1:]),
|
||||
AxisOption("[Postprocess] Face restore", str, apply_face_restore, fmt=format_value),
|
||||
AxisOptionImg2Img("Image mask weight", float, apply_field("inpainting_mask_weight")),
|
||||
AxisOption("Model dictionary", str, apply_dict, fmt=format_value, cost=1.0, choices=lambda: ['None'] + list(sd_models.checkpoints_list)),
|
||||
AxisOption("[Sampler] sigma min", float, apply_field("s_min")),
|
||||
AxisOption("[Sampler] sigma max", float, apply_field("s_max")),
|
||||
AxisOption("[Sampler] sigma tmin", float, apply_field("s_tmin")),
|
||||
AxisOption("[Sampler] sigma tmax", float, apply_field("s_tmax")),
|
||||
AxisOption("[Sampler] sigma Churn", float, apply_field("s_churn")),
|
||||
AxisOption("[Sampler] sigma noise", float, apply_field("s_noise")),
|
||||
AxisOption("[Sampler] eta", float, apply_field("eta")),
|
||||
AxisOption("[Sampler] solver order", int, apply_setting("schedulers_solver_order")),
|
||||
AxisOption("[Second pass] upscaler", str, apply_field("hr_upscaler"), choices=lambda: [*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]]),
|
||||
AxisOption("[Second pass] sampler", str, apply_latent_sampler, fmt=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers]),
|
||||
AxisOption("[Second pass] denoising Strength", float, apply_field("denoising_strength")),
|
||||
AxisOption("[Second pass] hires steps", int, apply_field("hr_second_pass_steps")),
|
||||
AxisOption("[Sampler] Sigma min", float, apply_field("s_min")),
|
||||
AxisOption("[Sampler] Sigma max", float, apply_field("s_max")),
|
||||
AxisOption("[Sampler] Sigma tmin", float, apply_field("s_tmin")),
|
||||
AxisOption("[Sampler] Sigma tmax", float, apply_field("s_tmax")),
|
||||
AxisOption("[Sampler] Sigma Churn", float, apply_field("s_churn")),
|
||||
AxisOption("[Sampler] Sigma noise", float, apply_field("s_noise")),
|
||||
AxisOption("[Sampler] ETA", float, apply_field("eta")),
|
||||
AxisOption("[Sampler] Solver order", int, apply_setting("schedulers_solver_order")),
|
||||
AxisOption("[Second pass] Upscaler", str, apply_field("hr_upscaler"), choices=lambda: [*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]]),
|
||||
AxisOption("[Second pass] Sampler", str, apply_latent_sampler, fmt=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers]),
|
||||
AxisOption("[Second pass] Denoising Strength", float, apply_field("denoising_strength")),
|
||||
AxisOption("[Second pass] Hires steps", int, apply_field("hr_second_pass_steps")),
|
||||
AxisOption("[Second pass] CFG scale", float, apply_field("image_cfg_scale")),
|
||||
AxisOption("[Second pass] guidance rescale", float, apply_field("diffusers_guidance_rescale")),
|
||||
AxisOption("[Refiner] model", str, apply_refiner, fmt=format_value, cost=1.0, choices=lambda: ['None'] + sorted(sd_models.checkpoints_list)),
|
||||
AxisOption("[Refiner] refiner start", float, apply_field("refiner_start")),
|
||||
AxisOption("[Refiner] refiner steps", float, apply_field("refiner_steps")),
|
||||
AxisOption("[TOME] Token merging ratio (txt2img)", float, apply_override('token_merging_ratio')),
|
||||
AxisOption("[TOME] Token merging ratio (hires)", float, apply_override('token_merging_ratio_hr')),
|
||||
AxisOption("[Second pass] Guidance rescale", float, apply_field("diffusers_guidance_rescale")),
|
||||
AxisOption("[Refiner] Model", str, apply_refiner, fmt=format_value, cost=1.0, choices=lambda: ['None'] + sorted(sd_models.checkpoints_list)),
|
||||
AxisOption("[Refiner] Refiner start", float, apply_field("refiner_start")),
|
||||
AxisOption("[Refiner] Refiner steps", float, apply_field("refiner_steps")),
|
||||
AxisOption("[ToMe] Token merging ratio (txt2img)", float, apply_override('token_merging_ratio')),
|
||||
AxisOption("[ToMe] Token merging ratio (hires)", float, apply_override('token_merging_ratio_hr')),
|
||||
AxisOption("[FreeU] 1st stage backbone factor", float, apply_setting('freeu_b1')),
|
||||
AxisOption("[FreeU] 2nd stage backbone factor", float, apply_setting('freeu_b2')),
|
||||
AxisOption("[FreeU] 1st stage skip factor", float, apply_setting('freeu_s1')),
|
||||
|
||||
Reference in New Issue
Block a user