| from __future__ import annotations |
|
|
| import argparse |
| import numpy as np |
| import torch |
| from PIL import Image |
| from diffusers import AutoencoderKL |
| from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5TokenizerFast |
|
|
| from dit_v6 import MMDiT |
|
|
| PROMPTS = [ |
| "a bowl of ramen with a soft boiled egg", |
| "a red fox sitting in a snowy forest", |
| "a lighthouse on a cliff at sunset", |
| "a wooden cabin in the mountains", |
| "a cup of coffee on a wooden table", |
| "a golden retriever running on a beach", |
| "a city street at night with neon signs", |
| "a bowl of fresh strawberries", |
| "a sailboat on a calm lake", |
| ] |
|
|
| @torch.no_grad() |
| def sample(model, seq, mask, pool, null_seq, null_mask, null_pool, steps, cfg, dev): |
| B = seq.shape[0] |
| x = torch.randn(B, 4, 32, 32, device=dev) |
| ns, nm, npo = null_seq.expand(B, -1, -1), null_mask.expand(B, -1), null_pool.expand(B, -1) |
| dt = 1.0 / steps |
| for i in range(steps): |
| t = torch.full((B,), i * dt, device=dev) |
| with torch.autocast("cuda", dtype=torch.bfloat16): |
| vc = model(x, t, seq, mask, pool) |
| vu = model(x, t, ns, nm, npo) |
| x = x + (vu + cfg * (vc - vu)).float() * dt |
| return x |
|
|
| @torch.no_grad() |
| def main(): |
| ap = argparse.ArgumentParser() |
| ap.add_argument("--ckpt", default="/root/runs/pm6/best.pt") |
| ap.add_argument("--vae", default="madebyollin/sdxl-vae-fp16-fix") |
| ap.add_argument("--clip", default="openai/clip-vit-base-patch32") |
| ap.add_argument("--t5", default="google/flan-t5-base") |
| ap.add_argument("--steps", type=int, default=50) |
| ap.add_argument("--cfg", type=float, default=5.0) |
| ap.add_argument("--t5-len", type=int, default=32) |
| ap.add_argument("--clip-len", type=int, default=40) |
| ap.add_argument("--out", default="/root/preview.png") |
| args = ap.parse_args() |
| dev = "cuda" |
|
|
| ck = torch.load(args.ckpt, map_location=dev) |
| c = ck["cfg"] |
| model = MMDiT(dim=c["dim"], depth=c["depth"], heads=c["heads"], mlp_hidden=c["mlp_hidden"], |
| t5_len=c["t5_len"]).to(dev).eval() |
| model.load_state_dict(ck["ema"]) |
| print(f"[preview] loaded {args.ckpt} step {ck['step']}", flush=True) |
|
|
| vae = AutoencoderKL.from_pretrained(args.vae).to(dev).half().eval() |
| vae_scale = vae.config.scaling_factor |
| t5_tok = T5TokenizerFast.from_pretrained(args.t5) |
| t5 = T5EncoderModel.from_pretrained(args.t5).to(dev).eval() |
| clip_tok = CLIPTokenizer.from_pretrained(args.clip) |
| clip_txt = CLIPTextModel.from_pretrained(args.clip).to(dev).eval() |
|
|
| def enc(strings): |
| te = t5_tok(strings, padding="max_length", max_length=args.t5_len, truncation=True, |
| return_tensors="pt").to(dev) |
| seq = t5(input_ids=te["input_ids"], attention_mask=te["attention_mask"]).last_hidden_state.float() |
| ce = clip_tok(strings, padding="max_length", max_length=args.clip_len, truncation=True, |
| return_tensors="pt").to(dev) |
| pool = clip_txt(input_ids=ce["input_ids"]).pooler_output.float() |
| return seq, te["attention_mask"].float(), pool |
|
|
| null_seq, null_mask, null_pool = enc([""]) |
|
|
| cell, pad, cols = 256, 8, 3 |
| rows = (len(PROMPTS) + cols - 1) // cols |
| sheet = Image.new("RGB", (cols * cell + (cols + 1) * pad, rows * cell + (rows + 1) * pad), (245, 246, 248)) |
|
|
| for i, prompt in enumerate(PROMPTS): |
| seq, mask, pool = enc([prompt]) |
| z = sample(model, seq, mask, pool, null_seq, null_mask, null_pool, args.steps, args.cfg, dev) |
| img = vae.decode((z / vae_scale).half()).sample.float() |
| img = ((img.clamp(-1, 1) + 1) / 2)[0].permute(1, 2, 0).cpu().numpy() |
| a = (img * 255).round().astype(np.uint8) |
| r, cc = divmod(i, cols) |
| sheet.paste(Image.fromarray(a), (pad + cc * (cell + pad), pad + r * (cell + pad))) |
| print(f"[preview] {i+1}/{len(PROMPTS)}: {prompt}", flush=True) |
|
|
| sheet.save(args.out) |
| print(f"[preview] wrote {args.out}", flush=True) |
|
|
| if __name__ == "__main__": |
| main() |
|
|
