ADM-G-512/README.md

ADM-G-512

Self-contained ADM-G checkpoint inside BiliSakura/ADM-diffusers. Runtime dependencies: this folder + PyPI diffusers/torch only.

Hub path

BiliSakura/ADM-diffusers/ADM-G-512

Demo

Settings used for this demo image: ADM-G-512, DDIMScheduler, num_inference_steps=50, guidance_scale=4.0, seed=42, class "golden retriever".

Layout

ADM-G-512/
├── pipeline.py
├── model_index.json
├── demo.png
├── unet/
├── classifier/
└── scheduler/

Load

from pathlib import Path
import torch
from diffusers import DDIMScheduler, DiffusionPipeline

model_dir = Path("./BiliSakura/ADM-diffusers/ADM-G-512")
pipe = DiffusionPipeline.from_pretrained(
    str(model_dir),
    local_files_only=True,
    custom_pipeline=str(model_dir / "pipeline.py"),
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
)
pipe = pipe.to("cuda")
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
class_id = pipe.get_label_ids("golden retriever")[0]
generator = torch.Generator(device="cuda").manual_seed(42)

out = pipe(
    class_labels=class_id,
    guidance_scale=4.0,
    num_inference_steps=50,
    generator=generator,
).images[0]
out