wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-09 04:52:32 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Merge branch 'comfyanonymous:master' into feature/maskpainting

Browse Source
This commit is contained in:
Dr.Lt.Data 2023-05-04 10:55:37 +09:00 committed by GitHub
commit f2eaafebb8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 70 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/extra_samplers/uni_pc.py
View File

@ -767,7 +767,7 @@ class UniPC:
model_x = self.model_fn(x, vec_t)
model_prev_list[-1] = model_x
if callback is not None:
callback(step_index, model_prev_list[-1], x)
callback(step_index, model_prev_list[-1], x, steps)
else:
raise NotImplementedError()
if denoise_to_zero:

8
comfy/samplers.py
View File

@ -623,7 +623,8 @@ class KSampler:
ddim_callback = None
if callback is not None:
ddim_callback = lambda pred_x0, i: callback(i, pred_x0, None)
total_steps = len(timesteps) - 1
ddim_callback = lambda pred_x0, i: callback(i, pred_x0, None, total_steps)
sampler = DDIMSampler(self.model, device=self.device)
sampler.make_schedule_timesteps(ddim_timesteps=timesteps, verbose=False)
@ -654,13 +655,14 @@ class KSampler:
noise = noise * sigmas[0]
k_callback = None
total_steps = len(sigmas) - 1
if callback is not None:
k_callback = lambda x: callback(x["i"], x["denoised"], x["x"])
k_callback = lambda x: callback(x["i"], x["denoised"], x["x"], total_steps)
if latent_image is not None:
noise += latent_image
if self.sampler == "dpm_fast":
samples = k_diffusion_sampling.sample_dpm_fast(self.model_k, noise, sigma_min, sigmas[0], self.steps, extra_args=extra_args, callback=k_callback, disable=disable_pbar)
samples = k_diffusion_sampling.sample_dpm_fast(self.model_k, noise, sigma_min, sigmas[0], total_steps, extra_args=extra_args, callback=k_callback, disable=disable_pbar)
elif self.sampler == "dpm_adaptive":
samples = k_diffusion_sampling.sample_dpm_adaptive(self.model_k, noise, sigma_min, sigmas[0], extra_args=extra_args, callback=k_callback, disable=disable_pbar)
else:

23
comfy/sd.py
View File

@ -514,11 +514,16 @@ class VAE:
self.device = device
def decode_tiled_(self, samples, tile_x=64, tile_y=64, overlap = 16):
steps = samples.shape[0] * utils.get_tiled_scale_steps(samples.shape[3], samples.shape[2], tile_x, tile_y, overlap)
steps += samples.shape[0] * utils.get_tiled_scale_steps(samples.shape[3], samples.shape[2], tile_x // 2, tile_y * 2, overlap)
steps += samples.shape[0] * utils.get_tiled_scale_steps(samples.shape[3], samples.shape[2], tile_x * 2, tile_y // 2, overlap)
pbar = utils.ProgressBar(steps)
decode_fn = lambda a: (self.first_stage_model.decode(1. / self.scale_factor * a.to(self.device)) + 1.0)
output = torch.clamp((
(utils.tiled_scale(samples, decode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = 8) +
utils.tiled_scale(samples, decode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = 8) +
utils.tiled_scale(samples, decode_fn, tile_x, tile_y, overlap, upscale_amount = 8))
(utils.tiled_scale(samples, decode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = 8, pbar = pbar) +
utils.tiled_scale(samples, decode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = 8, pbar = pbar) +
utils.tiled_scale(samples, decode_fn, tile_x, tile_y, overlap, upscale_amount = 8, pbar = pbar))
/ 3.0) / 2.0, min=0.0, max=1.0)
return output
@ -562,9 +567,15 @@ class VAE:
model_management.unload_model()
self.first_stage_model = self.first_stage_model.to(self.device)
pixel_samples = pixel_samples.movedim(-1,1).to(self.device)
samples = utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x, tile_y, overlap, upscale_amount = (1/8), out_channels=4)
samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x * 2, tile_y // 2, overlap, upscale_amount = (1/8), out_channels=4)
samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x // 2, tile_y * 2, overlap, upscale_amount = (1/8), out_channels=4)
steps = pixel_samples.shape[0] * utils.get_tiled_scale_steps(pixel_samples.shape[3], pixel_samples.shape[2], tile_x, tile_y, overlap)
steps += pixel_samples.shape[0] * utils.get_tiled_scale_steps(pixel_samples.shape[3], pixel_samples.shape[2], tile_x // 2, tile_y * 2, overlap)
steps += pixel_samples.shape[0] * utils.get_tiled_scale_steps(pixel_samples.shape[3], pixel_samples.shape[2], tile_x * 2, tile_y // 2, overlap)
pbar = utils.ProgressBar(steps)
samples = utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x, tile_y, overlap, upscale_amount = (1/8), out_channels=4, pbar=pbar)
samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x * 2, tile_y // 2, overlap, upscale_amount = (1/8), out_channels=4, pbar=pbar)
samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x // 2, tile_y * 2, overlap, upscale_amount = (1/8), out_channels=4, pbar=pbar)
samples /= 3.0
self.first_stage_model = self.first_stage_model.cpu()
samples = samples.cpu()

33
comfy/utils.py
View File

@ -1,4 +1,5 @@
import torch
import math
def load_torch_file(ckpt, safe_load=False):
if ckpt.lower().endswith(".safetensors"):
@ -62,8 +63,11 @@ def common_upscale(samples, width, height, upscale_method, crop):
s = samples
return torch.nn.functional.interpolate(s, size=(height, width), mode=upscale_method)
def get_tiled_scale_steps(width, height, tile_x, tile_y, overlap):
return math.ceil((height / (tile_y - overlap))) * math.ceil((width / (tile_x - overlap)))
@torch.inference_mode()
def tiled_scale(samples, function, tile_x=64, tile_y=64, overlap = 8, upscale_amount = 4, out_channels = 3):
def tiled_scale(samples, function, tile_x=64, tile_y=64, overlap = 8, upscale_amount = 4, out_channels = 3, pbar = None):
output = torch.empty((samples.shape[0], out_channels, round(samples.shape[2] * upscale_amount), round(samples.shape[3] * upscale_amount)), device="cpu")
for b in range(samples.shape[0]):
s = samples[b:b+1]
@ -83,6 +87,33 @@ def tiled_scale(samples, function, tile_x=64, tile_y=64, overlap = 8, upscale_am
mask[:,:,:,mask.shape[3]- 1 - t: mask.shape[3]- t] *= ((1.0/feather) * (t + 1))
out[:,:,round(y*upscale_amount):round((y+tile_y)*upscale_amount),round(x*upscale_amount):round((x+tile_x)*upscale_amount)] += ps * mask
out_div[:,:,round(y*upscale_amount):round((y+tile_y)*upscale_amount),round(x*upscale_amount):round((x+tile_x)*upscale_amount)] += mask
if pbar is not None:
pbar.update(1)
output[b:b+1] = out/out_div
return output
PROGRESS_BAR_HOOK = None
def set_progress_bar_global_hook(function):
global PROGRESS_BAR_HOOK
PROGRESS_BAR_HOOK = function
class ProgressBar:
def __init__(self, total):
global PROGRESS_BAR_HOOK
self.total = total
self.current = 0
self.hook = PROGRESS_BAR_HOOK
def update_absolute(self, value, total=None):
if total is not None:
self.total = total
if value > self.total:
value = self.total
self.current = value
if self.hook is not None:
self.hook(self.current, self.total)
def update(self, value):
self.update_absolute(self.current + value)

7
comfy_extras/nodes_upscale_model.py
View File

@ -37,7 +37,12 @@ class ImageUpscaleWithModel:
device = model_management.get_torch_device()
upscale_model.to(device)
in_img = image.movedim(-1,-3).to(device)
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=128 + 64, tile_y=128 + 64, overlap = 8, upscale_amount=upscale_model.scale)
tile = 128 + 64
overlap = 8
steps = in_img.shape[0] * comfy.utils.get_tiled_scale_steps(in_img.shape[3], in_img.shape[2], tile_x=tile, tile_y=tile, overlap=overlap)
pbar = comfy.utils.ProgressBar(steps)
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
upscale_model.cpu()
s = torch.clamp(s.movedim(-3,-1), min=0, max=1.0)
return (s,)

12
main.py
View File

@ -5,6 +5,7 @@ import shutil
import threading
from comfy.cli_args import args
import comfy.utils
if os.name == "nt":
import logging
@ -39,14 +40,9 @@ async def run(server, address='', port=8188, verbose=True, call_on_start=None):
await asyncio.gather(server.start(address, port, verbose, call_on_start), server.publish_loop())
def hijack_progress(server):
from tqdm.auto import tqdm
orig_func = getattr(tqdm, "update")
def wrapped_func(*args, **kwargs):
pbar = args[0]
v = orig_func(*args, **kwargs)
server.send_sync("progress", { "value": pbar.n, "max": pbar.total}, server.client_id)
return v
setattr(tqdm, "update", wrapped_func)
def hook(value, total):
server.send_sync("progress", { "value": value, "max": total}, server.client_id)
comfy.utils.set_progress_bar_global_hook(hook)
def cleanup_temp():
temp_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "temp")

6
nodes.py
View File

@ -815,9 +815,13 @@ def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive,
if "noise_mask" in latent:
noise_mask = latent["noise_mask"]
pbar = comfy.utils.ProgressBar(steps)
def callback(step, x0, x, total_steps):
pbar.update_absolute(step + 1, total_steps)
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
denoise=denoise, disable_noise=disable_noise, start_step=start_step, last_step=last_step,
force_full_denoise=force_full_denoise, noise_mask=noise_mask)
force_full_denoise=force_full_denoise, noise_mask=noise_mask, callback=callback)
out = latent.copy()
out["samples"] = samples
return (out, )