diff options
Diffstat (limited to 'modules/processing.py')
| -rw-r--r-- | modules/processing.py | 106 |
1 files changed, 70 insertions, 36 deletions
diff --git a/modules/processing.py b/modules/processing.py index 7eeb5191..8faf9095 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -1,4 +1,3 @@ -import contextlib
import json
import math
import os
@@ -12,9 +11,8 @@ import cv2 from skimage import exposure
import modules.sd_hijack
-from modules import devices, prompt_parser, masking
+from modules import devices, prompt_parser, masking, sd_samplers, lowvram
from modules.sd_hijack import model_hijack
-from modules.sd_samplers import samplers, samplers_for_img2img
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
import modules.face_restoration
@@ -56,7 +54,7 @@ class StableDiffusionProcessing: self.prompt: str = prompt
self.prompt_for_display: str = None
self.negative_prompt: str = (negative_prompt or "")
- self.styles: str = styles
+ self.styles: list = styles or []
self.seed: int = seed
self.subseed: int = subseed
self.subseed_strength: float = subseed_strength
@@ -79,13 +77,13 @@ class StableDiffusionProcessing: self.paste_to = None
self.color_corrections = None
self.denoising_strength: float = 0
-
+ self.sampler_noise_scheduler_override = None
self.ddim_discretize = opts.ddim_discretize
self.s_churn = opts.s_churn
self.s_tmin = opts.s_tmin
self.s_tmax = float('inf') # not representable as a standard ui option
self.s_noise = opts.s_noise
-
+
if not seed_enable_extras:
self.subseed = -1
self.subseed_strength = 0
@@ -111,7 +109,7 @@ class Processed: self.width = p.width
self.height = p.height
self.sampler_index = p.sampler_index
- self.sampler = samplers[p.sampler_index].name
+ self.sampler = sd_samplers.samplers[p.sampler_index].name
self.cfg_scale = p.cfg_scale
self.steps = p.steps
self.batch_size = p.batch_size
@@ -130,7 +128,7 @@ class Processed: self.s_tmin = p.s_tmin
self.s_tmax = p.s_tmax
self.s_noise = p.s_noise
-
+ self.sampler_noise_scheduler_override = p.sampler_noise_scheduler_override
self.prompt = self.prompt if type(self.prompt) != list else self.prompt[0]
self.negative_prompt = self.negative_prompt if type(self.negative_prompt) != list else self.negative_prompt[0]
self.seed = int(self.seed if type(self.seed) != list else self.seed[0])
@@ -249,9 +247,16 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see return x
+def get_fixed_seed(seed):
+ if seed is None or seed == '' or seed == -1:
+ return int(random.randrange(4294967294))
+
+ return seed
+
+
def fix_seed(p):
- p.seed = int(random.randrange(4294967294)) if p.seed is None or p.seed == '' or p.seed == -1 else p.seed
- p.subseed = int(random.randrange(4294967294)) if p.subseed is None or p.subseed == '' or p.subseed == -1 else p.subseed
+ p.seed = get_fixed_seed(p.seed)
+ p.subseed = get_fixed_seed(p.subseed)
def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration=0, position_in_batch=0):
@@ -259,7 +264,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration generation_params = {
"Steps": p.steps,
- "Sampler": samplers[p.sampler_index].name,
+ "Sampler": sd_samplers.samplers[p.sampler_index].name,
"CFG scale": p.cfg_scale,
"Seed": all_seeds[index],
"Face restoration": (opts.face_restoration_model if p.restore_faces else None),
@@ -271,7 +276,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration "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),
- "Eta": (None if p.sampler.eta == p.sampler.default_eta else p.sampler.eta),
+ "Eta": (None if p.sampler is None or p.sampler.eta == p.sampler.default_eta else p.sampler.eta),
}
generation_params.update(p.extra_generation_params)
@@ -290,13 +295,17 @@ def process_images(p: StableDiffusionProcessing) -> Processed: assert(len(p.prompt) > 0)
else:
assert p.prompt is not None
-
+
devices.torch_gc()
- fix_seed(p)
+ seed = get_fixed_seed(p.seed)
+ subseed = get_fixed_seed(p.subseed)
+
+ if p.outpath_samples is not None:
+ os.makedirs(p.outpath_samples, exist_ok=True)
- os.makedirs(p.outpath_samples, exist_ok=True)
- os.makedirs(p.outpath_grids, exist_ok=True)
+ if p.outpath_grids is not None:
+ os.makedirs(p.outpath_grids, exist_ok=True)
modules.sd_hijack.model_hijack.apply_circular(p.tiling)
@@ -309,28 +318,28 @@ def process_images(p: StableDiffusionProcessing) -> Processed: else:
all_prompts = p.batch_size * p.n_iter * [p.prompt]
- if type(p.seed) == list:
- all_seeds = p.seed
+ if type(seed) == list:
+ all_seeds = seed
else:
- all_seeds = [int(p.seed) + (x if p.subseed_strength == 0 else 0) for x in range(len(all_prompts))]
+ all_seeds = [int(seed) + (x if p.subseed_strength == 0 else 0) for x in range(len(all_prompts))]
- if type(p.subseed) == list:
- all_subseeds = p.subseed
+ if type(subseed) == list:
+ all_subseeds = subseed
else:
- all_subseeds = [int(p.subseed) + x for x in range(len(all_prompts))]
+ all_subseeds = [int(subseed) + x for x in range(len(all_prompts))]
def infotext(iteration=0, position_in_batch=0):
return create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration, position_in_batch)
if os.path.exists(cmd_opts.embeddings_dir):
- model_hijack.load_textual_inversion_embeddings(cmd_opts.embeddings_dir, p.sd_model)
+ model_hijack.embedding_db.load_textual_inversion_embeddings()
infotexts = []
output_images = []
- precision_scope = torch.autocast if cmd_opts.precision == "autocast" else contextlib.nullcontext
- ema_scope = (contextlib.nullcontext if cmd_opts.lowvram else p.sd_model.ema_scope)
- with torch.no_grad(), precision_scope("cuda"), ema_scope():
- p.init(all_prompts, all_seeds, all_subseeds)
+
+ with torch.no_grad():
+ with devices.autocast():
+ p.init(all_prompts, all_seeds, all_subseeds)
if state.job_count == -1:
state.job_count = p.n_iter
@@ -348,8 +357,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed: #uc = p.sd_model.get_learned_conditioning(len(prompts) * [p.negative_prompt])
#c = p.sd_model.get_learned_conditioning(prompts)
- uc = prompt_parser.get_learned_conditioning(len(prompts) * [p.negative_prompt], p.steps)
- c = prompt_parser.get_learned_conditioning(prompts, p.steps)
+ with devices.autocast():
+ uc = prompt_parser.get_learned_conditioning(shared.sd_model, len(prompts) * [p.negative_prompt], p.steps)
+ c = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, p.steps)
if len(model_hijack.comments) > 0:
for comment in model_hijack.comments:
@@ -358,16 +368,27 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if p.n_iter > 1:
shared.state.job = f"Batch {n+1} out of {p.n_iter}"
- samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)
+ with devices.autocast():
+ samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)
+
if state.interrupted:
# if we are interruped, sample returns just noise
# use the image collected previously in sampler loop
samples_ddim = shared.state.current_latent
+ samples_ddim = samples_ddim.to(devices.dtype)
+
x_samples_ddim = p.sd_model.decode_first_stage(samples_ddim)
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
+ del samples_ddim
+
+ if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
+ lowvram.send_everything_to_cpu()
+
+ devices.torch_gc()
+
if opts.filter_nsfw:
import modules.safety as safety
x_samples_ddim = modules.safety.censor_batch(x_samples_ddim)
@@ -383,6 +404,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: devices.torch_gc()
x_sample = modules.face_restoration.restore_faces(x_sample)
+ devices.torch_gc()
image = Image.fromarray(x_sample)
@@ -408,9 +430,15 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if opts.samples_save and not p.do_not_save_samples:
images.save_image(image, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p)
- infotexts.append(infotext(n, i))
+ text = infotext(n, i)
+ infotexts.append(text)
+ image.info["parameters"] = text
output_images.append(image)
+ del x_samples_ddim
+
+ devices.torch_gc()
+
state.nextjob()
p.color_corrections = None
@@ -421,7 +449,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed: grid = images.image_grid(output_images, p.batch_size)
if opts.return_grid:
- infotexts.insert(0, infotext())
+ text = infotext()
+ infotexts.insert(0, text)
+ grid.info["parameters"] = text
output_images.insert(0, grid)
index_of_first_image = 1
@@ -462,7 +492,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.firstphase_height_truncated = int(scale * self.height)
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
- self.sampler = samplers[self.sampler_index].constructor(self.sd_model)
+ self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)
if not self.enable_hr:
x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
@@ -505,13 +535,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): shared.state.nextjob()
- self.sampler = samplers[self.sampler_index].constructor(self.sd_model)
+ self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)
+
noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, 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)
return samples
@@ -540,7 +571,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.nmask = None
def init(self, all_prompts, all_seeds, all_subseeds):
- self.sampler = samplers_for_img2img[self.sampler_index].constructor(self.sd_model)
+ self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers_for_img2img, self.sampler_index, self.sd_model)
crop_region = None
if self.image_mask is not None:
@@ -647,4 +678,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): if self.mask is not None:
samples = samples * self.nmask + self.init_latent * self.mask
+ del x
+ devices.torch_gc()
+
return samples
|