indepth-10M / run_indepth.py
DexagonAI's picture
Upload folder using huggingface_hub
3711808 verified
Raw History Blame Contribute Delete
2.97 kB
#!/usr/bin/env python3
"""Run InDepth from the command line.
Usage:
python run_indepth.py "cat wearing green crown" --steps 4 --cfg 1.5 --seed 13372000
python run_indepth.py --prompts a.txt --out sprites/ # one prompt per line
python run_indepth.py --local /path/to/indepth-10M ... # local dir instead of the hub
Requires: torch, safetensors, huggingface_hub (for hub download), pillow.
"""
import argparse
import json
from pathlib import Path
import numpy as np
from PIL import Image
def main():
parser = argparse.ArgumentParser(description="Generate 16x16 RGBA sprites with InDepth")
parser.add_argument("prompt", nargs="?", help="text prompt (lowercase, short works best)")
parser.add_argument("--prompts", help="text file with one prompt per line")
parser.add_argument("--out", default="out/", help="output directory")
parser.add_argument("--local", help="local model directory (skips hub download)")
parser.add_argument("--steps", type=int, default=4, help="sampling steps (1-4)")
parser.add_argument("--cfg", type=float, default=1.5, help="classifier-free guidance (1 = off)")
parser.add_argument("--seed", type=int, default=13372000)
parser.add_argument("--device", default="cpu", help="'cpu' or 'cuda'")
parser.add_argument("--scale", type=int, default=8, help="PNG upscale factor (nearest)")
args = parser.parse_args()
if not args.prompt and not args.prompts:
parser.error("give a prompt or --prompts file")
from modeling_indepth import decode_to_rgba, generate, load_indepth
from tokenizer import IndepthTokenizer
model_dir = args.local or "DexagonAI/indepth-10M"
model, config, resolved_dir = load_indepth(model_dir)
tokenizer = IndepthTokenizer(resolved_dir)
print(f"loaded {sum(p.numel() for p in model.parameters()):,} params, "
f"vocab {len(tokenizer.stoi)} words, {config.subword_buckets} subword buckets")
prompts = [args.prompt] if args.prompt else [l.strip() for l in Path(args.prompts).read_text().splitlines() if l.strip()]
device = args.device
model = model.to(device)
token_rows, sub_rows = tokenizer.batch(prompts)
import torch
tokens = torch.tensor(token_rows, dtype=torch.long)
subwords = torch.tensor(sub_rows, dtype=torch.long)
image = generate(model, config, tokens, subwords, seed=args.seed, steps=args.steps, guidance=args.cfg, device=device)
rgba = decode_to_rgba(image)
out_dir = Path(args.out)
out_dir.mkdir(parents=True, exist_ok=True)
for i, prompt in enumerate(prompts):
sprite = Image.fromarray(rgba[i], "RGBA").resize(
(16 * args.scale, 16 * args.scale), Image.Resampling.NEAREST)
slug = "-".join(w for w in __import__("re").split(r"[^a-z0-9]+", prompt.lower()) if w)[:40] or "sprite"
path = out_dir / f"{slug}_{args.seed}_{i}.png"
sprite.save(path)
print("wrote", path)
if __name__ == "__main__":
main()