InvokeAI 2.2.4.5__py3-none-any.whl

scripts/orig_scripts/train_searcher.py

@@ -0,0 +1,147 @@
+import os, sys
+import numpy as np
+import scann
+import argparse
+import glob
+from multiprocessing import cpu_count
+from tqdm import tqdm
+
+from ldm.util import parallel_data_prefetch
+
+
+def search_bruteforce(searcher):
+    return searcher.score_brute_force().build()
+
+
+def search_partioned_ah(searcher, dims_per_block, aiq_threshold, reorder_k,
+                        partioning_trainsize, num_leaves, num_leaves_to_search):
+    return searcher.tree(num_leaves=num_leaves,
+                         num_leaves_to_search=num_leaves_to_search,
+                         training_sample_size=partioning_trainsize). \
+        score_ah(dims_per_block, anisotropic_quantization_threshold=aiq_threshold).reorder(reorder_k).build()
+
+
+def search_ah(searcher, dims_per_block, aiq_threshold, reorder_k):
+    return searcher.score_ah(dims_per_block, anisotropic_quantization_threshold=aiq_threshold).reorder(
+        reorder_k).build()
+
+def load_datapool(dpath):
+
+
+    def load_single_file(saved_embeddings):
+        compressed = np.load(saved_embeddings)
+        database = {key: compressed[key] for key in compressed.files}
+        return database
+
+    def load_multi_files(data_archive):
+        database = {key: [] for key in data_archive[0].files}
+        for d in tqdm(data_archive, desc=f'Loading datapool from {len(data_archive)} individual files.'):
+            for key in d.files:
+                database[key].append(d[key])
+
+        return database
+
+    print(f'Load saved patch embedding from "{dpath}"')
+    file_content = glob.glob(os.path.join(dpath, '*.npz'))
+
+    if len(file_content) == 1:
+        data_pool = load_single_file(file_content[0])
+    elif len(file_content) > 1:
+        data = [np.load(f) for f in file_content]
+        prefetched_data = parallel_data_prefetch(load_multi_files, data,
+                                                 n_proc=min(len(data), cpu_count()), target_data_type='dict')
+
+        data_pool = {key: np.concatenate([od[key] for od in prefetched_data], axis=1)[0] for key in prefetched_data[0].keys()}
+    else:
+        raise ValueError(f'No npz-files in specified path "{dpath}" is this directory existing?')
+
+    print(f'Finished loading of retrieval database of length {data_pool["embedding"].shape[0]}.')
+    return data_pool
+
+
+def train_searcher(opt,
+                   metric='dot_product',
+                   partioning_trainsize=None,
+                   reorder_k=None,
+                   # todo tune
+                   aiq_thld=0.2,
+                   dims_per_block=2,
+                   num_leaves=None,
+                   num_leaves_to_search=None,):
+
+    data_pool = load_datapool(opt.database)
+    k = opt.knn
+
+    if not reorder_k:
+        reorder_k = 2 * k
+
+    # normalize
+    # embeddings =
+    searcher = scann.scann_ops_pybind.builder(data_pool['embedding'] / np.linalg.norm(data_pool['embedding'], axis=1)[:, np.newaxis], k, metric)
+    pool_size = data_pool['embedding'].shape[0]
+
+    print(*(['#'] * 100))
+    print('Initializing scaNN searcher with the following values:')
+    print(f'k: {k}')
+    print(f'metric: {metric}')
+    print(f'reorder_k: {reorder_k}')
+    print(f'anisotropic_quantization_threshold: {aiq_thld}')
+    print(f'dims_per_block: {dims_per_block}')
+    print(*(['#'] * 100))
+    print('Start training searcher....')
+    print(f'N samples in pool is {pool_size}')
+
+    # this reflects the recommended design choices proposed at
+    # https://github.com/google-research/google-research/blob/aca5f2e44e301af172590bb8e65711f0c9ee0cfd/scann/docs/algorithms.md
+    if pool_size < 2e4:
+        print('Using brute force search.')
+        searcher = search_bruteforce(searcher)
+    elif 2e4 <= pool_size and pool_size < 1e5:
+        print('Using asymmetric hashing search and reordering.')
+        searcher = search_ah(searcher, dims_per_block, aiq_thld, reorder_k)
+    else:
+        print('Using using partioning, asymmetric hashing search and reordering.')
+
+        if not partioning_trainsize:
+            partioning_trainsize = data_pool['embedding'].shape[0] // 10
+        if not num_leaves:
+            num_leaves = int(np.sqrt(pool_size))
+
+        if not num_leaves_to_search:
+            num_leaves_to_search = max(num_leaves // 20, 1)
+
+        print('Partitioning params:')
+        print(f'num_leaves: {num_leaves}')
+        print(f'num_leaves_to_search: {num_leaves_to_search}')
+        # self.searcher = self.search_ah(searcher, dims_per_block, aiq_thld, reorder_k)
+        searcher = search_partioned_ah(searcher, dims_per_block, aiq_thld, reorder_k,
+                                                 partioning_trainsize, num_leaves, num_leaves_to_search)
+
+    print('Finish training searcher')
+    searcher_savedir = opt.target_path
+    os.makedirs(searcher_savedir, exist_ok=True)
+    searcher.serialize(searcher_savedir)
+    print(f'Saved trained searcher under "{searcher_savedir}"')
+
+if __name__ == '__main__':
+    sys.path.append(os.getcwd())
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--database',
+                        '-d',
+                        default='data/rdm/retrieval_databases/openimages',
+                        type=str,
+                        help='path to folder containing the clip feature of the database')
+    parser.add_argument('--target_path',
+                        '-t',
+                        default='data/rdm/searchers/openimages',
+                        type=str,
+                        help='path to the target folder where the searcher shall be stored.')
+    parser.add_argument('--knn',
+                        '-k',
+                        default=20,
+                        type=int,
+                        help='number of nearest neighbors, for which the searcher shall be optimized')
+
+    opt, _  = parser.parse_known_args()
+
+    train_searcher(opt,)

scripts/orig_scripts/txt2img.py

@@ -0,0 +1,324 @@
+import argparse, os, sys, glob
+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
+import time
+from pytorch_lightning import seed_everything
+from torch import autocast
+from contextlib import contextmanager, nullcontext
+
+import k_diffusion as K
+import torch.nn as nn
+
+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 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(
+        "--outdir",
+        type=str,
+        nargs="?",
+        help="dir to write results to",
+        default="outputs/txt2img-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 individual 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(
+        "--klms",
+        action='store_true',
+        help="use klms sampling",
+    )
+    parser.add_argument(
+        "--laion400m",
+        action='store_true',
+        help="uses the LAION400M model",
+    )
+    parser.add_argument(
+        "--fixed_code",
+        action='store_true',
+        help="if enabled, uses the same starting code across 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=2,
+        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",
+    )
+    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=7.5,
+        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",
+    )
+    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()
+
+    if opt.laion400m:
+        print("Falling back to LAION 400M model...")
+        opt.config = "configs/latent-diffusion/txt2img-1p4B-eval.yaml"
+        opt.ckpt = "models/ldm/text2img-large/model.ckpt"
+        opt.outdir = "outputs/txt2img-samples-laion400m"
+
+
+    config = OmegaConf.load(f"{opt.config}")
+    model = load_model_from_config(config, f"{opt.ckpt}")
+
+    seed_everything(opt.seed)
+
+    device = torch.device(choose_torch_device())
+    model  = model.to(device)
+
+    #for klms
+    model_wrap = K.external.CompVisDenoiser(model)
+    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
+
+    if opt.plms:
+        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()
+            if (len(data) >= batch_size):
+                data = list(chunk(data, batch_size))
+            else:
+                while (len(data) < batch_size):
+                    data.append(data[-1])
+                data = [data]
+
+    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 opt.fixed_code:
+        shape = [opt.n_samples, opt.C, opt.H // opt.f, opt.W // opt.f]
+        if device.type == 'mps':
+            start_code = torch.randn(shape, device='cpu').to(device)
+        else:
+            torch.randn(shape, device=device)
+
+    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)
+                        shape = [opt.C, opt.H // opt.f, opt.W // opt.f]
+
+                        if not opt.klms:
+                            samples_ddim, _ = sampler.sample(S=opt.ddim_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)
+                        else:
+                            sigmas = model_wrap.get_sigmas(opt.ddim_steps)
+                            if start_code:
+                                x = start_code
+                            else:
+                                x = torch.randn([opt.n_samples, *shape], device=device) * sigmas[0] # for GPU draw
+                            model_wrap_cfg = CFGDenoiser(model_wrap)
+                            extra_args = {'cond': c, 'uncond': uc, 'cond_scale': opt.scale}
+                            samples_ddim = K.sampling.sample_lms(model_wrap_cfg, x, sigmas, extra_args=extra_args)
+
+                        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.fromarray(x_sample.astype(np.uint8)).save(
+                                    os.path.join(sample_path, f"{base_count:05}.png"))
+                                base_count += 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'))
+                    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/preload_models.py

@@ -0,0 +1,12 @@
+#!/usr/bin/env python
+# Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
+# Before running stable-diffusion on an internet-isolated machine,
+# run this script from one with internet connectivity. The
+# two machines must share a common .cache directory.
+
+import warnings
+import configure_invokeai
+
+if __name__ == '__main__':
+    configure_invokeai.main()
+

scripts/sd-metadata.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+
+import sys
+import json
+from ldm.invoke.pngwriter import retrieve_metadata
+
+if len(sys.argv) < 2:
+    print("Usage: file2prompt.py <file1.png> <file2.png> <file3.png>...")
+    print("This script opens up the indicated invoke.py-generated PNG file(s) and prints out their metadata.")
+    exit(-1)
+
+filenames = sys.argv[1:]
+for f in filenames:
+    try:
+        metadata = retrieve_metadata(f)
+        print(f'{f}:\n',json.dumps(metadata['sd-metadata'], indent=4))
+    except FileNotFoundError:
+        sys.stderr.write(f'{f} not found\n')
+        continue
+    except PermissionError:
+        sys.stderr.write(f'{f} could not be opened due to inadequate permissions\n')
+        continue

vendored/clip/clip/__init__.py

@@ -0,0 +1 @@
+from .clip import *