diff options
Diffstat (limited to 'modules/processing.py')
| -rw-r--r-- | modules/processing.py | 60 |
1 files changed, 43 insertions, 17 deletions
diff --git a/modules/processing.py b/modules/processing.py index afab6790..2e5a363f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -186,7 +186,7 @@ class StableDiffusionProcessing: return conditioning
def edit_image_conditioning(self, source_image):
- conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
+ conditioning_image = self.sd_model.encode_first_stage(source_image).mode()
return conditioning_image
@@ -268,6 +268,7 @@ class Processed: self.height = p.height
self.sampler_name = p.sampler_name
self.cfg_scale = p.cfg_scale
+ self.image_cfg_scale = getattr(p, 'image_cfg_scale', None)
self.steps = p.steps
self.batch_size = p.batch_size
self.restore_faces = p.restore_faces
@@ -445,19 +446,17 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Steps": p.steps,
"Sampler": p.sampler_name,
"CFG scale": p.cfg_scale,
+ "Image CFG scale": getattr(p, 'image_cfg_scale', None),
"Seed": all_seeds[index],
"Face restoration": (opts.face_restoration_model if p.restore_faces else None),
"Size": f"{p.width}x{p.height}",
"Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
"Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
- "Batch size": (None if p.batch_size < 2 else p.batch_size),
- "Batch pos": (None if p.batch_size < 2 else position_in_batch),
"Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
"Variation seed strength": (None if p.subseed_strength == 0 else p.subseed_strength),
"Seed resize from": (None if p.seed_resize_from_w == 0 or p.seed_resize_from_h == 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
"Denoising strength": getattr(p, 'denoising_strength', None),
"Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None,
- "Eta": (None if p.sampler is None or p.sampler.eta == p.sampler.default_eta else p.sampler.eta),
"Clip skip": None if clip_skip <= 1 else clip_skip,
"ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta,
}
@@ -544,8 +543,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if os.path.exists(cmd_opts.embeddings_dir) and not p.do_not_reload_embeddings:
model_hijack.embedding_db.load_textual_inversion_embeddings()
- _, extra_network_data = extra_networks.parse_prompts(p.all_prompts[0:1])
-
if p.scripts is not None:
p.scripts.process(p)
@@ -583,16 +580,10 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if shared.opts.live_previews_enable and opts.show_progress_type == "Approx NN":
sd_vae_approx.model()
- if not p.disable_extra_networks:
- extra_networks.activate(p, extra_network_data)
-
- with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file:
- processed = Processed(p, [], p.seed, "")
- file.write(processed.infotext(p, 0))
-
if state.job_count == -1:
state.job_count = p.n_iter
+ extra_network_data = None
for n in range(p.n_iter):
p.iteration = n
@@ -607,14 +598,30 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]
+ if p.scripts is not None:
+ p.scripts.before_process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
+
if len(prompts) == 0:
break
- prompts, _ = extra_networks.parse_prompts(prompts)
+ prompts, extra_network_data = extra_networks.parse_prompts(prompts)
+
+ if not p.disable_extra_networks:
+ with devices.autocast():
+ extra_networks.activate(p, extra_network_data)
if p.scripts is not None:
p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
+ # params.txt should be saved after scripts.process_batch, since the
+ # infotext could be modified by that callback
+ # Example: a wildcard processed by process_batch sets an extra model
+ # strength, which is saved as "Model Strength: 1.0" in the infotext
+ if n == 0:
+ with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file:
+ processed = Processed(p, [], p.seed, "")
+ file.write(processed.infotext(p, 0))
+
uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc)
c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c)
@@ -682,6 +689,22 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: image.info["parameters"] = text
output_images.append(image)
+ if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay:
+ image_mask = p.mask_for_overlay.convert('RGB')
+ image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), p.mask_for_overlay.convert('L')).convert('RGBA')
+
+ if opts.save_mask:
+ images.save_image(image_mask, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask")
+
+ if opts.save_mask_composite:
+ images.save_image(image_mask_composite, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask-composite")
+
+ if opts.return_mask:
+ output_images.append(image_mask)
+
+ if opts.return_mask_composite:
+ output_images.append(image_mask_composite)
+
del x_samples_ddim
devices.torch_gc()
@@ -706,7 +729,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if opts.grid_save:
images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True)
- if not p.disable_extra_networks:
+ if not p.disable_extra_networks and extra_network_data:
extra_networks.deactivate(p, extra_network_data)
devices.torch_gc()
@@ -885,7 +908,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): shared.state.nextjob()
- img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM' # PLMS does not support img2img so we just silently switch ot DDIM
+ img2img_sampler_name = self.sampler_name
+ if self.sampler_name in ['PLMS', 'UniPC']: # PLMS/UniPC do not support img2img so we just silently switch to DDIM
+ img2img_sampler_name = 'DDIM'
self.sampler = sd_samplers.create_sampler(img2img_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]
@@ -904,12 +929,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
sampler = None
- def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):
+ def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, image_cfg_scale: float = None, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):
super().__init__(**kwargs)
self.init_images = init_images
self.resize_mode: int = resize_mode
self.denoising_strength: float = denoising_strength
+ self.image_cfg_scale: float = image_cfg_scale if shared.sd_model.cond_stage_key == "edit" else None
self.init_latent = None
self.image_mask = mask
self.latent_mask = None
|