InvokeAI 2.2.4.5__py3-none-any.whl

scripts/merge_embeddings.py

@@ -0,0 +1,124 @@
+from ldm.modules.encoders.modules import FrozenCLIPEmbedder, BERTEmbedder
+from ldm.modules.embedding_manager import EmbeddingManager
+from ldm.invoke.globals import Globals
+
+import argparse, os
+from functools import partial
+
+import torch
+
+def get_placeholder_loop(placeholder_string, embedder, use_bert):
+
+    new_placeholder   = None
+
+    while True:
+        if new_placeholder is None:
+            new_placeholder = input(f"Placeholder string {placeholder_string} was already used. Please enter a replacement string: ")
+        else:
+            new_placeholder = input(f"Placeholder string '{new_placeholder}' maps to more than a single token. Please enter another string: ")
+
+        token = get_bert_token_for_string(embedder.tknz_fn, new_placeholder) if use_bert else get_clip_token_for_string(embedder.tokenizer, new_placeholder)
+
+        if token is not None:
+            return new_placeholder, token
+
+def get_clip_token_for_string(tokenizer, string):
+    batch_encoding = tokenizer(
+        string,
+        truncation=True,
+        max_length=77,
+        return_length=True,
+        return_overflowing_tokens=False,
+        padding="max_length",
+        return_tensors="pt"
+    )
+
+    tokens = batch_encoding["input_ids"]
+
+    if torch.count_nonzero(tokens - 49407) == 2:
+        return tokens[0, 1]
+
+    return None
+
+def get_bert_token_for_string(tokenizer, string):
+    token = tokenizer(string)
+    if torch.count_nonzero(token) == 3:
+        return token[0, 1]
+
+    return None
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "--root_dir",
+        type=str,
+        default='.',
+        help="Path to the InvokeAI install directory containing 'models', 'outputs' and 'configs'."
+    )
+
+    parser.add_argument(
+        "--manager_ckpts",
+        type=str,
+        nargs="+",
+        required=True,
+        help="Paths to a set of embedding managers to be merged."
+    )
+
+    parser.add_argument(
+        "--output_path",
+        type=str,
+        required=True,
+        help="Output path for the merged manager",
+    )
+
+    parser.add_argument(
+        "-sd", "--use_bert",
+        action="store_true",
+        help="Flag to denote that we are not merging stable diffusion embeddings"
+    )
+
+    args = parser.parse_args()
+    Globals.root=args.root_dir
+
+    if args.use_bert:
+        embedder = BERTEmbedder(n_embed=1280, n_layer=32).cuda()
+    else:
+        embedder = FrozenCLIPEmbedder().cuda()
+
+    EmbeddingManager = partial(EmbeddingManager, embedder, ["*"])
+
+    string_to_token_dict = {}
+    string_to_param_dict = torch.nn.ParameterDict()
+
+    placeholder_to_src = {}
+
+    for manager_ckpt in args.manager_ckpts:
+        print(f"Parsing {manager_ckpt}...")
+
+        manager = EmbeddingManager()
+        manager.load(manager_ckpt)
+
+        for placeholder_string in manager.string_to_token_dict:
+            if not placeholder_string in string_to_token_dict:
+                string_to_token_dict[placeholder_string] = manager.string_to_token_dict[placeholder_string]
+                string_to_param_dict[placeholder_string] = manager.string_to_param_dict[placeholder_string]
+
+                placeholder_to_src[placeholder_string] = manager_ckpt
+            else:
+                new_placeholder, new_token = get_placeholder_loop(placeholder_string, embedder, use_bert=args.use_bert)
+                string_to_token_dict[new_placeholder] = new_token
+                string_to_param_dict[new_placeholder] = manager.string_to_param_dict[placeholder_string]
+
+                placeholder_to_src[new_placeholder] = manager_ckpt
+
+    print("Saving combined manager...")
+    merged_manager = EmbeddingManager()
+    merged_manager.string_to_param_dict = string_to_param_dict
+    merged_manager.string_to_token_dict = string_to_token_dict
+    merged_manager.save(args.output_path)
+
+    print("Managers merged. Final list of placeholders: ")
+    print(placeholder_to_src)

scripts/orig_scripts/img2img.py

@@ -0,0 +1,296 @@
+"""make variations of input image"""
+
+import argparse, os, sys, glob
+import PIL
+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, repeat
+from torchvision.utils import make_grid
+from torch import autocast
+from contextlib import nullcontext
+import time
+from pytorch_lightning import seed_everything
+
+from ldm.util import instantiate_from_config
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.models.diffusion.plms import PLMSSampler
+from ldm.invoke.devices         import choose_torch_device
+
+
+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.to(choose_torch_device())
+    model.eval()
+    return model
+
+
+def load_img(path):
+    image = Image.open(path).convert("RGB")
+    w, h = image.size
+    print(f"loaded input image of size ({w}, {h}) from {path}")
+    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    image = image.resize((w, h), resample=PIL.Image.LANCZOS)
+    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 main():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "--prompt",
+        type=str,
+        nargs="?",
+        default="a painting of a virus monster playing guitar",
+        help="the prompt to render"
+    )
+
+    parser.add_argument(
+        "--init-img",
+        type=str,
+        nargs="?",
+        help="path to the input image"
+    )
+
+    parser.add_argument(
+        "--outdir",
+        type=str,
+        nargs="?",
+        help="dir to write results to",
+        default="outputs/img2img-samples"
+    )
+
+    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(
+        "--ddim_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(
+        "--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=1,
+        help="sample this often",
+    )
+    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=2,
+        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=5.0,
+        help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
+    )
+
+    parser.add_argument(
+        "--strength",
+        type=float,
+        default=0.75,
+        help="strength for noising/unnoising. 1.0 corresponds to full destruction of information in init image",
+    )
+    parser.add_argument(
+        "--from-file",
+        type=str,
+        help="if specified, load prompts from this file",
+    )
+    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(
+        "--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"
+    )
+
+    opt = parser.parse_args()
+    seed_everything(opt.seed)
+
+    config = OmegaConf.load(f"{opt.config}")
+    model = load_model_from_config(config, f"{opt.ckpt}")
+
+    device = torch.device(choose_torch_device())
+    model = model.to(device)
+
+    if opt.plms:
+        raise NotImplementedError("PLMS sampler not (yet) supported")
+        sampler = PLMSSampler(model)
+    else:
+        sampler = DDIMSampler(model)
+
+    os.makedirs(opt.outdir, exist_ok=True)
+    outpath = opt.outdir
+
+    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 = list(chunk(data, batch_size))
+
+    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
+
+    assert os.path.isfile(opt.init_img)
+    init_image = load_img(opt.init_img).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
+
+    sampler.make_schedule(ddim_num_steps=opt.ddim_steps, ddim_eta=opt.ddim_eta, verbose=False)
+
+    assert 0. <= opt.strength <= 1., 'can only work with strength in [0.0, 1.0]'
+    t_enc = int(opt.strength * opt.ddim_steps)
+    print(f"target t_enc is {t_enc} steps")
+
+    precision_scope = autocast if opt.precision == "autocast" else nullcontext
+    if device.type in ['mps', 'cpu']:
+        precision_scope = nullcontext # have to use f32 on mps
+    with torch.no_grad():
+        with precision_scope(device.type):
+            with model.ema_scope():
+                tic = time.time()
+                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)
+
+                        # encode (scaled latent)
+                        z_enc = sampler.stochastic_encode(init_latent, torch.tensor([t_enc]*batch_size).to(device))
+                        # decode it
+                        samples = sampler.decode(z_enc, c, t_enc, unconditional_guidance_scale=opt.scale,
+                                                 unconditional_conditioning=uc,)
+
+                        x_samples = model.decode_first_stage(samples)
+                        x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0)
+
+                        if not opt.skip_save:
+                            for x_sample in x_samples:
+                                x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
+                                Image.fromarray(x_sample.astype(np.uint8)).save(
+                                    os.path.join(sample_path, f"{base_count:05}.png"))
+                                base_count += 1
+                        all_samples.append(x_samples)
+
+                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'))
+                    grid_count += 1
+
+                toc = time.time()
+
+    print(f"Your samples are ready and waiting for you here: \n{outpath} \n"
+          f" \nEnjoy.")
+
+
+if __name__ == "__main__":
+    main()

scripts/orig_scripts/inpaint.py

@@ -0,0 +1,98 @@
+import argparse, os, sys, glob
+from omegaconf import OmegaConf
+from PIL import Image
+from tqdm import tqdm
+import numpy as np
+import torch
+from main import instantiate_from_config
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.invoke.devices import choose_torch_device
+
+def make_batch(image, mask, device):
+    image = np.array(Image.open(image).convert("RGB"))
+    image = image.astype(np.float32)/255.0
+    image = image[None].transpose(0,3,1,2)
+    image = torch.from_numpy(image)
+
+    mask = np.array(Image.open(mask).convert("L"))
+    mask = mask.astype(np.float32)/255.0
+    mask = mask[None,None]
+    mask[mask < 0.5] = 0
+    mask[mask >= 0.5] = 1
+    mask = torch.from_numpy(mask)
+
+    masked_image = (1-mask)*image
+
+    batch = {"image": image, "mask": mask, "masked_image": masked_image}
+    for k in batch:
+        batch[k] = batch[k].to(device=device)
+        batch[k] = batch[k]*2.0-1.0
+    return batch
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--indir",
+        type=str,
+        nargs="?",
+        help="dir containing image-mask pairs (`example.png` and `example_mask.png`)",
+    )
+    parser.add_argument(
+        "--outdir",
+        type=str,
+        nargs="?",
+        help="dir to write results to",
+    )
+    parser.add_argument(
+        "--steps",
+        type=int,
+        default=50,
+        help="number of ddim sampling steps",
+    )
+    opt = parser.parse_args()
+
+    masks = sorted(glob.glob(os.path.join(opt.indir, "*_mask.png")))
+    images = [x.replace("_mask.png", ".png") for x in masks]
+    print(f"Found {len(masks)} inputs.")
+
+    config = OmegaConf.load("models/ldm/inpainting_big/config.yaml")
+    model = instantiate_from_config(config.model)
+    model.load_state_dict(torch.load("models/ldm/inpainting_big/last.ckpt")["state_dict"],
+                          strict=False)
+
+    device  = choose_torch_device()
+    model   = model.to(device)
+    sampler = DDIMSampler(model)
+
+    os.makedirs(opt.outdir, exist_ok=True)
+    with torch.no_grad():
+        with model.ema_scope():
+            for image, mask in tqdm(zip(images, masks)):
+                outpath = os.path.join(opt.outdir, os.path.split(image)[1])
+                batch = make_batch(image, mask, device=device)
+
+                # encode masked image and concat downsampled mask
+                c = model.cond_stage_model.encode(batch["masked_image"])
+                cc = torch.nn.functional.interpolate(batch["mask"],
+                                                     size=c.shape[-2:])
+                c = torch.cat((c, cc), dim=1)
+
+                shape = (c.shape[1]-1,)+c.shape[2:]
+                samples_ddim, _ = sampler.sample(S=opt.steps,
+                                                 conditioning=c,
+                                                 batch_size=c.shape[0],
+                                                 shape=shape,
+                                                 verbose=False)
+                x_samples_ddim = model.decode_first_stage(samples_ddim)
+
+                image = torch.clamp((batch["image"]+1.0)/2.0,
+                                    min=0.0, max=1.0)
+                mask = torch.clamp((batch["mask"]+1.0)/2.0,
+                                   min=0.0, max=1.0)
+                predicted_image = torch.clamp((x_samples_ddim+1.0)/2.0,
+                                              min=0.0, max=1.0)
+
+                inpainted = (1-mask)*image+mask*predicted_image
+                inpainted = inpainted.cpu().numpy().transpose(0,2,3,1)[0]*255
+                Image.fromarray(inpainted.astype(np.uint8)).save(outpath)