StableDiffusion/scripts/txt2img.py

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

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

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, device=torch.device("cuda"), 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)

    if device == torch.device("cuda"):
        model.cuda()
    elif device == torch.device("cpu"):
        model.cpu()
        model.cond_stage_model.device = "cpu"
    else:
        raise ValueError(f"Incorrect device name. Received: {device}")
    model.eval()
    return model


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(
        "--n_prompt",
        type=str,
        nargs="?",
        default="",
        help="the negative 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",
    )
    parser.add_argument(
        "--device",
        type=str,
        help="Device on which Stable Diffusion will be run",
        choices=["cpu", "cuda"],
        default="cpu"
    )
    parser.add_argument(
        "--torchscript",
        action='store_true',
        help="Use TorchScript",
    )
    parser.add_argument(
        "--ipex",
        action='store_true',
        help="Use Intel® Extension for PyTorch*",
    )
    parser.add_argument(
        "--bf16",
        action='store_true',
        help="Use bfloat16",
    )
    opt = parser.parse_args()
    return opt


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


def main(opt):
    seed_everything(opt.seed)

    config = OmegaConf.load(f"{opt.config}")
    device = torch.device("cuda") if opt.device == "cuda" else torch.device("cpu")
    model = load_model_from_config(config, f"{opt.ckpt}", device)

    if opt.plms:
        sampler = PLMSSampler(model, device=device)
    elif opt.dpm:
        sampler = DPMSolverSampler(model, device=device)
    else:
        sampler = DDIMSampler(model, device=device)

    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))

    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

    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)

    if opt.torchscript or opt.ipex:
        transformer = model.cond_stage_model.model
        unet = model.model.diffusion_model
        decoder = model.first_stage_model.decoder
        additional_context = torch.cpu.amp.autocast() if opt.bf16 else nullcontext()
        shape = [opt.C, opt.H // opt.f, opt.W // opt.f]

        if opt.bf16 and not opt.torchscript and not opt.ipex:
            raise ValueError('Bfloat16 is supported only for torchscript+ipex')
        if opt.bf16 and unet.dtype != torch.bfloat16:
            raise ValueError("Use configs/stable-diffusion/intel/ configs with bf16 enabled if " +
                             "you'd like to use bfloat16 with CPU.")
        if unet.dtype == torch.float16 and device == torch.device("cpu"):
            raise ValueError("Use configs/stable-diffusion/intel/ configs for your model if you'd like to run it on CPU.")

        if opt.ipex:
            import intel_extension_for_pytorch as ipex
            bf16_dtype = torch.bfloat16 if opt.bf16 else None
            transformer = transformer.to(memory_format=torch.channels_last)
            transformer = ipex.optimize(transformer, level="O1", inplace=True)

            unet = unet.to(memory_format=torch.channels_last)
            unet = ipex.optimize(unet, level="O1", auto_kernel_selection=True, inplace=True, dtype=bf16_dtype)

            decoder = decoder.to(memory_format=torch.channels_last)
            decoder = ipex.optimize(decoder, level="O1", auto_kernel_selection=True, inplace=True, dtype=bf16_dtype)

        if opt.torchscript:
            with torch.no_grad(), additional_context:
                # get UNET scripted
                if unet.use_checkpoint:
                    raise ValueError("Gradient checkpoint won't work with tracing. " +
                    "Use configs/stable-diffusion/intel/ configs for your model or disable checkpoint in your config.")

                img_in = torch.ones(2, 4, 96, 96, dtype=torch.float32)
                t_in = torch.ones(2, dtype=torch.int64)
                context = torch.ones(2, 77, 1024, dtype=torch.float32)
                scripted_unet = torch.jit.trace(unet, (img_in, t_in, context))
                scripted_unet = torch.jit.optimize_for_inference(scripted_unet)
                print(type(scripted_unet))
                model.model.scripted_diffusion_model = scripted_unet

                # get Decoder for first stage model scripted
                samples_ddim = torch.ones(1, 4, 96, 96, dtype=torch.float32)
                scripted_decoder = torch.jit.trace(decoder, (samples_ddim))
                scripted_decoder = torch.jit.optimize_for_inference(scripted_decoder)
                print(type(scripted_decoder))
                model.first_stage_model.decoder = scripted_decoder

        prompts = data[0]
        print("Running a forward pass to initialize optimizations")
        uc = None
        if opt.n_prompt == "":
            if opt.scale != 1.0:
                uc = model.get_learned_conditioning(batch_size * [""])
        else:
            uc = model.get_learned_conditioning(opt.n_prompt)
        if isinstance(prompts, tuple):
            prompts = list(prompts)

        with torch.no_grad(), additional_context:
            for _ in range(3):
                c = model.get_learned_conditioning(prompts)
            samples_ddim, _ = sampler.sample(S=5,
                                             conditioning=c,
                                             batch_size=batch_size,
                                             shape=shape,
                                             verbose=False,
                                             unconditional_guidance_scale=opt.scale,
                                             unconditional_conditioning=uc,
                                             eta=opt.ddim_eta,
                                             x_T=start_code)
            print("Running a forward pass for decoder")
            for _ in range(3):
                x_samples_ddim = model.decode_first_stage(samples_ddim)

    precision_scope = autocast if opt.precision=="autocast" or opt.bf16 else nullcontext
    with torch.no_grad(), \
        precision_scope(opt.device), \
        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)
                        img.save(os.path.join(sample_path, f"{base_count:05}.png"))
                        base_count += 1
                        sample_count += 1

                    all_samples.append(x_samples)

            # 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()
            grid = Image.fromarray(grid.astype(np.uint8))
            grid = put_watermark(grid, wm_encoder)
            grid.save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
            grid_count += 1

    print(f"Your samples are ready and waiting for you here: \n{outpath} \n"
          f" \nEnjoy.")


if __name__ == "__main__":
    opt = parse_args()
    main(opt)