diff options
| -rw-r--r-- | README.md | 60 | ||||
| -rw-r--r-- | screenshot.png | bin | 0 -> 885798 bytes | |||
| -rw-r--r-- | webui.py | 404 |
3 files changed, 462 insertions, 2 deletions
@@ -1,2 +1,58 @@ -# stable-diffusion-webui -Stable Diffusion web UI +# Stable Diffusion web UI
+A browser interface based on Gradio library for Stable Diffusion.
+
+Original script with Gradio UI was written by a kind anonymopus user. This is a modification.
+
+
+
+## Stable Diffusion
+
+This script assumes that you already have main Stable Diffusion sutff installed, assumed to be in directory `/sd`.
+If you don't have it installed, follow the guide:
+
+- https://rentry.org/kretard
+
+This repository's `webgui.py` is a replacement for `kdiff.py` from the guide.
+
+Particularly, following files must exist:
+
+- `/sd/configs/stable-diffusion/v1-inference.yaml`
+- `/sd/models/ldm/stable-diffusion-v1/model.ckpt`
+- `/sd/ldm/util.py`
+- `/sd/k_diffusion/__init__.py`
+
+## GFPGAN
+
+If you want to use GFPGAN to improve generated faces, you need to install it separately.
+Follow instructions from https://github.com/TencentARC/GFPGAN, but when cloning it, do so into Stable Diffusion main directory, `/sd`.
+After that download [GFPGANv1.3.pth](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth) and put it
+into the `/sd/GFPGAN/experiments/pretrained_models` directory. If you're getting troubles with GFPGAN support, follow instructions
+from the GFPGAN's repository until `inference_gfpgan.py` script works.
+
+The following files must exist:
+
+- `/sd/GFPGAN/inference_gfpgan.py`
+- `/sd/GFPGAN/experiments/pretrained_models/GFPGANv1.3.pth`
+
+If the GFPGAN directory does not exist, you will not get the option to use GFPGAN in the UI. If it does exist, you will either be able
+to use it, or there will be a message in console with an error related to GFPGAN.
+
+## Web UI
+
+Run the script as:
+
+`python webui.py`
+
+When running the script, you must be in the main Stable Diffusion directory, `/sd`. If you cloned this repository into a subdirectory
+of `/sd`, say, the `stable-diffusion-webui` directory, you will run it as:
+
+`python stable-diffusion-webui/webui.py`
+
+When launching, you may get a very long warning message related to some weights not being used. You may freely ignore it.
+After a while, you will get a message like this:
+
+```
+Running on local URL: http://127.0.0.1:7860/
+```
+
+Open the URL in browser, and you are good to go.
diff --git a/screenshot.png b/screenshot.png Binary files differnew file mode 100644 index 00000000..7e13a0de --- /dev/null +++ b/screenshot.png diff --git a/webui.py b/webui.py new file mode 100644 index 00000000..b0d67f31 --- /dev/null +++ b/webui.py @@ -0,0 +1,404 @@ +import PIL
+import argparse, os, sys, glob
+import torch
+import torch.nn as nn
+import numpy as np
+import gradio as gr
+from omegaconf import OmegaConf
+from PIL import Image
+from itertools import islice
+from einops import rearrange, repeat
+from torchvision.utils import make_grid
+from torch import autocast
+from contextlib import contextmanager, nullcontext
+import mimetypes
+import random
+
+import k_diffusion as K
+from ldm.util import instantiate_from_config
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.models.diffusion.plms import PLMSSampler
+
+# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the bowser will not show any UI
+mimetypes.init()
+mimetypes.add_type('application/javascript', '.js')
+
+# some of those options should not be changed at all because they would break the model, so I removed them from options.
+opt_C = 4
+opt_f = 8
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--outdir", type=str, nargs="?", help="dir to write results to", default=None)
+parser.add_argument("--skip_grid", action='store_true', help="do not save a grid, only individual samples. Helpful when evaluating lots of samples",)
+parser.add_argument("--skip_save", action='store_true', help="do not save indiviual samples. For speed measurements.",)
+parser.add_argument("--n_rows", type=int, default=0, help="rows in the grid (default: n_samples)",)
+parser.add_argument("--config", type=str, default="configs/stable-diffusion/v1-inference.yaml", help="path to config which constructs model",)
+parser.add_argument("--ckpt", type=str, default="models/ldm/stable-diffusion-v1/model.ckpt", help="path to checkpoint of model",)
+parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
+parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default='./GFPGAN')
+opt = parser.parse_args()
+
+GFPGAN_dir = opt.gfpgan_dir
+
+
+def chunk(it, size):
+ it = iter(it)
+ return iter(lambda: tuple(islice(it, size)), ())
+
+
+def load_model_from_config(config, ckpt, verbose=False):
+ print(f"Loading model from {ckpt}")
+ pl_sd = torch.load(ckpt, map_location="cpu")
+ if "global_step" in pl_sd:
+ print(f"Global Step: {pl_sd['global_step']}")
+ sd = pl_sd["state_dict"]
+ model = instantiate_from_config(config.model)
+ m, u = model.load_state_dict(sd, strict=False)
+ if len(m) > 0 and verbose:
+ print("missing keys:")
+ print(m)
+ if len(u) > 0 and verbose:
+ print("unexpected keys:")
+ print(u)
+
+ model.cuda()
+ model.eval()
+ return model
+
+
+def load_img_pil(img_pil):
+ image = img_pil.convert("RGB")
+ w, h = image.size
+ print(f"loaded input image of size ({w}, {h})")
+ w, h = map(lambda x: x - x % 64, (w, h)) # resize to integer multiple of 64
+ image = image.resize((w, h), resample=PIL.Image.LANCZOS)
+ print(f"cropped image to size ({w}, {h})")
+ image = np.array(image).astype(np.float32) / 255.0
+ image = image[None].transpose(0, 3, 1, 2)
+ image = torch.from_numpy(image)
+ return 2. * image - 1.
+
+
+def load_img(path):
+ return load_img_pil(Image.open(path))
+
+
+class CFGDenoiser(nn.Module):
+ def __init__(self, model):
+ super().__init__()
+ self.inner_model = model
+
+ def forward(self, x, sigma, uncond, cond, cond_scale):
+ x_in = torch.cat([x] * 2)
+ sigma_in = torch.cat([sigma] * 2)
+ cond_in = torch.cat([uncond, cond])
+ uncond, cond = self.inner_model(x_in, sigma_in, cond=cond_in).chunk(2)
+ return uncond + (cond - uncond) * cond_scale
+
+
+def load_GFPGAN():
+ model_name = 'GFPGANv1.3'
+ model_path = os.path.join(GFPGAN_dir, 'experiments/pretrained_models', model_name + '.pth')
+ if not os.path.isfile(model_path):
+ raise Exception("GFPGAN model not found at path "+model_path)
+
+ sys.path.append(os.path.abspath(GFPGAN_dir))
+ from gfpgan import GFPGANer
+
+ return GFPGANer(model_path=model_path, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None)
+
+
+GFPGAN = None
+if os.path.exists(GFPGAN_dir):
+ try:
+ GFPGAN = load_GFPGAN()
+ print("Loaded GFPGAN")
+ except Exception:
+ import traceback
+ print("Error loading GFPGAN:", file=sys.stderr)
+ print(traceback.format_exc(), file=sys.stderr)
+
+config = OmegaConf.load("configs/stable-diffusion/v1-inference.yaml")
+model = load_model_from_config(config, "models/ldm/stable-diffusion-v1/model.ckpt")
+
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+model = model.half().to(device)
+
+
+def image_grid(imgs, rows):
+ cols = len(imgs) // rows
+
+ w, h = imgs[0].size
+ grid = Image.new('RGB', size=(cols * w, rows * h))
+
+ for i, img in enumerate(imgs):
+ grid.paste(img, box=(i % cols * w, i // cols * h))
+
+ return grid
+
+def dream(prompt: str, ddim_steps: int, sampler_name: str, fixed_code: bool, use_GFPGAN: bool, ddim_eta: float, n_iter: int, n_samples: int, cfg_scale: float, seed: int, height: int, width: int):
+ torch.cuda.empty_cache()
+
+ outpath = opt.outdir or "outputs/txt2img-samples"
+
+ if seed == -1:
+ seed = random.randrange(4294967294)
+
+ seed = int(seed)
+
+ is_PLMS = sampler_name == 'PLMS'
+ is_DDIM = sampler_name == 'DDIM'
+ is_Kdif = sampler_name == 'k-diffusion'
+
+ sampler = None
+ if is_PLMS:
+ sampler = PLMSSampler(model)
+ elif is_DDIM:
+ sampler = DDIMSampler(model)
+ elif is_Kdif:
+ pass
+ else:
+ raise Exception("Unknown sampler: " + sampler_name)
+
+ model_wrap = K.external.CompVisDenoiser(model)
+
+ os.makedirs(outpath, exist_ok=True)
+
+ batch_size = n_samples
+ n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
+
+ assert prompt is not None
+ data = [batch_size * [prompt]]
+
+ sample_path = os.path.join(outpath, "samples")
+ os.makedirs(sample_path, exist_ok=True)
+ base_count = len(os.listdir(sample_path))
+ grid_count = len(os.listdir(outpath)) - 1
+
+ start_code = None
+ if fixed_code:
+ start_code = torch.randn([n_samples, opt_C, height // opt_f, width // opt_f], device=device)
+
+ precision_scope = autocast if opt.precision == "autocast" else nullcontext
+ output_images = []
+ with torch.no_grad(), precision_scope("cuda"), model.ema_scope():
+ all_samples = []
+
+ for n in range(n_iter):
+ for batch_index, prompts in enumerate(data):
+ uc = None
+ if cfg_scale != 1.0:
+ uc = model.get_learned_conditioning(batch_size * [""])
+ if isinstance(prompts, tuple):
+ prompts = list(prompts)
+ c = model.get_learned_conditioning(prompts)
+ shape = [opt_C, height // opt_f, width // opt_f]
+
+ current_seed = seed + n * len(data) + batch_index
+ torch.manual_seed(current_seed)
+
+ if is_Kdif:
+ sigmas = model_wrap.get_sigmas(ddim_steps)
+ x = torch.randn([n_samples, *shape], device=device) * sigmas[0] # for GPU draw
+ model_wrap_cfg = CFGDenoiser(model_wrap)
+ samples_ddim = K.sampling.sample_lms(model_wrap_cfg, x, sigmas, extra_args={'cond': c, 'uncond': uc, 'cond_scale': cfg_scale}, disable=False)
+
+ elif sampler is not None:
+ samples_ddim, _ = sampler.sample(S=ddim_steps, conditioning=c, batch_size=n_samples, shape=shape, verbose=False, unconditional_guidance_scale=cfg_scale, unconditional_conditioning=uc, eta=ddim_eta, x_T=start_code)
+
+ x_samples_ddim = model.decode_first_stage(samples_ddim)
+ x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
+
+ if not opt.skip_save or not opt.skip_grid:
+ for x_sample in x_samples_ddim:
+ x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
+ x_sample = x_sample.astype(np.uint8)
+
+ if use_GFPGAN and GFPGAN is not None:
+ cropped_faces, restored_faces, restored_img = GFPGAN.enhance(x_sample, has_aligned=False, only_center_face=False, paste_back=True)
+ x_sample = restored_img
+
+ image = Image.fromarray(x_sample)
+
+ image.save(os.path.join(sample_path, f"{base_count:05}-{current_seed}_{prompt.replace(' ', '_')[:128]}.png"))
+ output_images.append(image)
+ base_count += 1
+
+ if not opt.skip_grid:
+ all_samples.append(x_sample)
+
+ if not opt.skip_grid:
+ # additionally, save as grid
+ grid = image_grid(output_images, rows=n_rows)
+ grid.save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
+ grid_count += 1
+
+
+ if sampler is not None:
+ del sampler
+
+ info = f"""
+{prompt}
+Steps: {ddim_steps}, Sampler: {sampler_name}, CFG scale: {cfg_scale}, Seed: {seed}{', GFPGAN' if use_GFPGAN and GFPGAN is not None else ''}
+ """.strip()
+
+ return output_images, seed, info
+
+
+dream_interface = gr.Interface(
+ dream,
+ inputs=[
+ gr.Textbox(label="Prompt", placeholder="A corgi wearing a top hat as an oil painting.", lines=1),
+ gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=50),
+ gr.Radio(label='Sampling method', choices=["DDIM", "PLMS", "k-diffusion"], value="k-diffusion"),
+ gr.Checkbox(label='Enable Fixed Code sampling', value=False),
+ gr.Checkbox(label='Fix faces using GFPGAN', value=False, visible=GFPGAN is not None),
+ gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="DDIM ETA", value=0.0, visible=False),
+ gr.Slider(minimum=1, maximum=16, step=1, label='Sampling iterations', value=1),
+ gr.Slider(minimum=1, maximum=4, step=1, label='Samples per iteration', value=1),
+ gr.Slider(minimum=1.0, maximum=15.0, step=0.5, label='Classifier Free Guidance Scale', value=7.0),
+ gr.Number(label='Seed', value=-1),
+ gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512),
+ gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512),
+ ],
+ outputs=[
+ gr.Gallery(label="Images"),
+ gr.Number(label='Seed'),
+ gr.Textbox(label="Copy-paste generation parameters"),
+ ],
+ title="Stable Diffusion Text-to-Image K",
+ description="Generate images from text with Stable Diffusion (using K-LMS)",
+ allow_flagging="never"
+)
+
+
+def translation(prompt: str, init_img, ddim_steps: int, ddim_eta: float, n_iter: int, n_samples: int, cfg_scale: float, denoising_strength: float, seed: int, height: int, width: int):
+ torch.cuda.empty_cache()
+
+ outpath = opt.outdir or "outputs/img2img-samples"
+
+ if seed == -1:
+ seed = random.randrange(4294967294)
+
+ sampler = DDIMSampler(model)
+
+ model_wrap = K.external.CompVisDenoiser(model)
+
+ os.makedirs(outpath, exist_ok=True)
+
+ batch_size = n_samples
+ n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
+
+ assert prompt is not None
+ data = [batch_size * [prompt]]
+
+ sample_path = os.path.join(outpath, "samples")
+ os.makedirs(sample_path, exist_ok=True)
+ base_count = len(os.listdir(sample_path))
+ grid_count = len(os.listdir(outpath)) - 1
+ seedit = 0
+
+ image = init_img.convert("RGB")
+ w, h = image.size
+ image = np.array(image).astype(np.float32) / 255.0
+ image = image[None].transpose(0, 3, 1, 2)
+ image = torch.from_numpy(image)
+
+ output_images = []
+ precision_scope = autocast if opt.precision == "autocast" else nullcontext
+ with torch.no_grad():
+ with precision_scope("cuda"):
+ init_image = 2. * image - 1.
+ init_image = init_image.to(device)
+ init_image = repeat(init_image, '1 ... -> b ...', b=batch_size)
+ init_latent = model.get_first_stage_encoding(model.encode_first_stage(init_image)) # move to latent space
+ x0 = init_latent
+
+ sampler.make_schedule(ddim_num_steps=ddim_steps, ddim_eta=ddim_eta, verbose=False)
+
+ assert 0. <= denoising_strength <= 1., 'can only work with strength in [0.0, 1.0]'
+ t_enc = int(denoising_strength * ddim_steps)
+ print(f"target t_enc is {t_enc} steps")
+ with model.ema_scope():
+ all_samples = list()
+ for n in range(n_iter):
+ for batch_index, prompts in enumerate(data):
+ uc = None
+ if cfg_scale != 1.0:
+ uc = model.get_learned_conditioning(batch_size * [""])
+ if isinstance(prompts, tuple):
+ prompts = list(prompts)
+ c = model.get_learned_conditioning(prompts)
+
+ sigmas = model_wrap.get_sigmas(ddim_steps)
+
+ current_seed = seed + n * len(data) + batch_index
+ torch.manual_seed(current_seed)
+
+ noise = torch.randn_like(x0) * sigmas[ddim_steps - t_enc - 1] # for GPU draw
+ xi = x0 + noise
+ sigma_sched = sigmas[ddim_steps - t_enc - 1:]
+ # x = torch.randn([n_samples, *shape]).to(device) * sigmas[0] # for CPU draw
+ model_wrap_cfg = CFGDenoiser(model_wrap)
+ extra_args = {'cond': c, 'uncond': uc, 'cond_scale': cfg_scale}
+
+ samples_ddim = K.sampling.sample_lms(model_wrap_cfg, xi, sigma_sched, extra_args=extra_args, disable=False)
+ x_samples_ddim = model.decode_first_stage(samples_ddim)
+ x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
+
+ if not opt.skip_save:
+ for x_sample in x_samples_ddim:
+ x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
+ image = Image.fromarray(x_sample.astype(np.uint8))
+ image.save(os.path.join(sample_path, f"{base_count:05}-{current_seed}_{prompt.replace(' ', '_')[:128]}.png"))
+ output_images.append(image)
+ base_count += 1
+ seedit += 1
+
+ if not opt.skip_grid:
+ all_samples.append(x_samples_ddim)
+
+ if not opt.skip_grid:
+ # additionally, save as grid
+ grid = torch.stack(all_samples, 0)
+ grid = rearrange(grid, 'n b c h w -> (n b) c h w')
+ grid = make_grid(grid, nrow=n_rows)
+
+ # to image
+ grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
+ Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
+ Image.fromarray(grid.astype(np.uint8))
+ grid_count += 1
+
+ del sampler
+ return output_images, seed
+
+
+# prompt, init_img, ddim_steps, plms, ddim_eta, n_iter, n_samples, cfg_scale, denoising_strength, seed
+
+img2img_interface = gr.Interface(
+ translation,
+ inputs=[
+ gr.Textbox(placeholder="A fantasy landscape, trending on artstation.", lines=1),
+ gr.Image(value="https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg", source="upload", interactive=True, type="pil"),
+ gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=50),
+ gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="DDIM ETA", value=0.0, visible=False),
+ gr.Slider(minimum=1, maximum=50, step=1, label='Sampling iterations', value=2),
+ gr.Slider(minimum=1, maximum=8, step=1, label='Samples per iteration', value=2),
+ gr.Slider(minimum=1.0, maximum=15.0, step=0.5, label='Classifier Free Guidance Scale', value=7.0),
+ gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising Strength', value=0.75),
+ gr.Number(label='Seed', value=-1),
+ gr.Slider(minimum=64, maximum=2048, step=64, label="Resize Height", value=512),
+ gr.Slider(minimum=64, maximum=2048, step=64, label="Resize Width", value=512),
+ ],
+ outputs=[
+ gr.Gallery(),
+ gr.Number(label='Seed')
+ ],
+ title="Stable Diffusion Image-to-Image",
+ description="Generate images from images with Stable Diffusion",
+)
+
+demo = gr.TabbedInterface(interface_list=[dream_interface, img2img_interface], tab_names=["Dream", "Image Translation"])
+
+demo.launch()
|
