import gradio as gr import argparse, os import cv2 import torch import numpy as np from omegaconf import OmegaConf from PIL import Image from tqdm import tqdm, trange from itertools import islice from einops import rearrange from torchvision.utils import make_grid from pytorch_lightning import seed_everything from torch import autocast from contextlib import nullcontext from imwatermark import WatermarkEncoder import re from ldm.util import instantiate_from_config from ldm.models.diffusion.ddim import DDIMSampler from ldm.models.diffusion.plms import PLMSSampler from ldm.models.diffusion.dpm_solver import DPMSolverSampler from huggingface_hub import hf_hub_download from datasets import load_dataset torch.set_grad_enabled(False) from share_btn import community_icon_html, loading_icon_html, share_js REPO_ID = "stabilityai/stable-diffusion-2" CKPT_NAME = "768-v-ema.ckpt" CONFIG_PATH = "./configs/stable-diffusion/v2-inference-v.yaml" device = "cuda" stable_diffusion_2_path = hf_hub_download(repo_id=REPO_ID, filename=CKPT_NAME) torch.set_grad_enabled(False) 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 put_watermark(img, wm_encoder=None): if wm_encoder is not None: img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR) img = wm_encoder.encode(img, 'dwtDct') img = Image.fromarray(img[:, :, ::-1]) return img #When running locally, you won`t have access to this, so you can remove this part word_list_dataset = load_dataset("stabilityai/word-list", data_files="list.txt", use_auth_token=True) word_list = word_list_dataset["train"]['text'] config = OmegaConf.load(CONFIG_PATH) model = load_model_from_config(config, stable_diffusion_2_path) device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu") model = model.to(device) def parse_args(): parser = argparse.ArgumentParser() parser.add_argument( "--prompt", type=str, nargs="?", default="a professional photograph of an astronaut riding a triceratops", help="the prompt to render" ) parser.add_argument( "--outdir", type=str, nargs="?", help="dir to write results to", default="outputs/txt2img-samples" ) parser.add_argument( "--steps", type=int, default=50, help="number of ddim sampling steps", ) parser.add_argument( "--plms", action='store_true', help="use plms sampling", ) parser.add_argument( "--dpm", action='store_true', help="use DPM (2) sampler", ) parser.add_argument( "--fixed_code", action='store_true', help="if enabled, uses the same starting code across all samples ", ) parser.add_argument( "--ddim_eta", type=float, default=0.0, help="ddim eta (eta=0.0 corresponds to deterministic sampling", ) parser.add_argument( "--n_iter", type=int, default=3, help="sample this often", ) parser.add_argument( "--H", type=int, default=512, help="image height, in pixel space", ) parser.add_argument( "--W", type=int, default=512, help="image width, in pixel space", ) parser.add_argument( "--C", type=int, default=4, help="latent channels", ) parser.add_argument( "--f", type=int, default=8, help="downsampling factor, most often 8 or 16", ) parser.add_argument( "--n_samples", type=int, default=3, help="how many samples to produce for each given prompt. A.k.a batch size", ) parser.add_argument( "--n_rows", type=int, default=0, help="rows in the grid (default: n_samples)", ) parser.add_argument( "--scale", type=float, default=9.0, help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))", ) parser.add_argument( "--from-file", type=str, help="if specified, load prompts from this file, separated by newlines", ) parser.add_argument( "--config", type=str, default="configs/stable-diffusion/v2-inference.yaml", help="path to config which constructs model", ) parser.add_argument( "--ckpt", type=str, help="path to checkpoint of model", ) parser.add_argument( "--seed", type=int, default=42, help="the seed (for reproducible sampling)", ) parser.add_argument( "--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast" ) parser.add_argument( "--repeat", type=int, default=1, help="repeat each prompt in file this often", ) opt = parser.parse_args() return opt def infer(prompt, samples, steps, scale, seed): opt = parse_args() opt.seed = seed seed_everything(seed) for filter in word_list: if re.search(rf"\b{filter}\b", prompt): raise gr.Error("Unsafe content found. Please try again with different prompts.") opt.n_samples = samples opt.scale = scale opt.prompt = prompt opt.steps = steps opt.n_iter = 1 sampler = DPMSolverSampler(model) os.makedirs(opt.outdir, exist_ok=True) outpath = opt.outdir print("Creating invisible watermark encoder (see https://github.com/ShieldMnt/invisible-watermark)...") wm = "SDV2" wm_encoder = WatermarkEncoder() wm_encoder.set_watermark('bytes', wm.encode('utf-8')) batch_size = opt.n_samples n_rows = opt.n_rows if opt.n_rows > 0 else batch_size if not opt.from_file: prompt = opt.prompt assert prompt is not None data = [batch_size * [prompt]] else: print(f"reading prompts from {opt.from_file}") with open(opt.from_file, "r") as f: data = f.read().splitlines() data = [p for p in data for i in range(opt.repeat)] data = list(chunk(data, batch_size)) prompt = prompt assert prompt is not None data = [batch_size * [prompt]] sample_path = os.path.join(outpath, "samples") os.makedirs(sample_path, exist_ok=True) sample_count = 0 base_count = len(os.listdir(sample_path)) grid_count = len(os.listdir(outpath)) - 1 opt.W = 768 opt.H = 768 start_code = None if opt.fixed_code: start_code = torch.randn([opt.n_samples, opt.C, opt.H // opt.f, opt.W // opt.f], device=device) precision_scope = autocast if opt.precision == "autocast" else nullcontext image_samples = [] with torch.no_grad(), \ precision_scope("cuda"), \ model.ema_scope(): all_samples = list() for n in trange(opt.n_iter, desc="Sampling"): for prompts in tqdm(data, desc="data"): uc = None if opt.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, opt.H // opt.f, opt.W // opt.f] samples, _ = sampler.sample(S=opt.steps, conditioning=c, batch_size=opt.n_samples, shape=shape, verbose=False, unconditional_guidance_scale=opt.scale, unconditional_conditioning=uc, eta=opt.ddim_eta, x_T=start_code) x_samples = model.decode_first_stage(samples) x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0) for x_sample in x_samples: x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c') img = Image.fromarray(x_sample.astype(np.uint8)) img = put_watermark(img, wm_encoder) image_samples.append(img) base_count += 1 sample_count += 1 all_samples.append(x_samples) return image_samples css = """ .gradio-container { font-family: 'IBM Plex Sans', sans-serif; } .gr-button { color: white; border-color: black; background: black; } input[type='range'] { accent-color: black; } .dark input[type='range'] { accent-color: #dfdfdf; } .container { max-width: 730px; margin: auto; padding-top: 1.5rem; } #gallery { min-height: 22rem; margin-bottom: 15px; margin-left: auto; margin-right: auto; border-bottom-right-radius: .5rem !important; border-bottom-left-radius: .5rem !important; } #gallery>div>.h-full { min-height: 20rem; } .details:hover { text-decoration: underline; } .gr-button { white-space: nowrap; } .gr-button:focus { border-color: rgb(147 197 253 / var(--tw-border-opacity)); outline: none; box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); --tw-border-opacity: 1; --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); --tw-ring-opacity: .5; } #advanced-btn { font-size: .7rem !important; line-height: 19px; margin-top: 12px; margin-bottom: 12px; padding: 2px 8px; border-radius: 14px !important; } #advanced-options { display: none; margin-bottom: 20px; } .footer { margin-bottom: 45px; margin-top: 35px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } .acknowledgments h4{ margin: 1.25em 0 .25em 0; font-weight: bold; font-size: 115%; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;right:0; } #share-btn * { all: unset; } #share-btn-container div:nth-child(-n+2){ width: auto !important; min-height: 0px !important; } #share-btn-container .wrap { display: none !important; } .gr-form{ flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0; } #prompt-container{ gap: 0; } """ block = gr.Blocks(css=css) examples = [ [ 'A high tech solarpunk utopia in the Amazon rainforest', 4, 45, 7.5, 1024, ], [ 'A pikachu fine dining with a view to the Eiffel Tower', 4, 45, 7, 1024, ], [ 'A mecha robot in a favela in expressionist style', 4, 45, 7, 1024, ], [ 'an insect robot preparing a delicious meal', 4, 45, 7, 1024, ], [ "A small cabin on top of a snowy mountain in the style of Disney, artstation", 4, 45, 7, 1024, ], ] with block: gr.HTML( """

Stable Diffusion 2 Demo

Stable Diffusion 2 is the latest text-to-image model from StabilityAI. Access Stable Diffusion 1 Space here
For faster generation and API access you can try DreamStudio Beta

""" ) with gr.Group(): with gr.Box(): with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True): text = gr.Textbox( label="Enter your prompt", show_label=False, max_lines=1, placeholder="Enter your prompt", elem_id="prompt-text-input", ).style( border=(True, False, True, True), rounded=(True, False, False, True), container=False, ) btn = gr.Button("Generate image").style( margin=False, rounded=(False, True, True, False), full_width=False, ) gallery = gr.Gallery( label="Generated images", show_label=False, elem_id="gallery" ).style(grid=[2], height="auto") with gr.Group(): with gr.Group(elem_id="share-btn-container"): community_icon = gr.HTML(community_icon_html) loading_icon = gr.HTML(loading_icon_html) share_button = gr.Button("Share to community", elem_id="share-btn") with gr.Accordion("Custom options", open=False): samples = gr.Slider(label="Images", minimum=1, maximum=4, value=4, step=1) steps = gr.Slider(label="Steps", minimum=1, maximum=50, value=25, step=1) scale = gr.Slider( label="Guidance Scale", minimum=0, maximum=50, value=9, step=0.1 ) seed = gr.Slider( label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True, ) ex = gr.Examples(examples=examples, fn=infer, inputs=[text, samples, steps, scale, seed], outputs=[gallery, community_icon, loading_icon, share_button], cache_examples=False) ex.dataset.headers = [""] text.submit(infer, inputs=[text, samples, steps, scale, seed], outputs=[gallery]) btn.click(infer, inputs=[text, samples, steps, scale, seed], outputs=[gallery]) share_button.click( None, [], [], _js=share_js, ) gr.HTML( """

LICENSE

The model is licensed with a CC-BY license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please read the license

Biases and content acknowledgment

Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the LAION-5B dataset, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the model card

""" ) block.queue(concurrency_count=1, max_size=25).launch(max_threads=150)