1
stars
25
commits
1
repos using this model
1
linked in READMEs
May 29, 2026
updated
Self-contained OpenAI ADM-G checkpoints for Hugging Face diffusers. No external code repo is required — each subfolder ships its own pipeline.py, component modules, and weights.
This repo is derived from the development bundle in Visual-Generative-Foundation-Model-Collection, but inference only needs:
BiliSakura/ADM-diffusers)diffusers, torch, huggingface_hubThis Hugging Face repo hosts multiple self-contained checkpoints as subfolders. Each subfolder includes its own pipeline.py, model_index.json, weights, and component code (unet/, classifier/, scheduler/).
| Subfolder | Resolution | Guidance scale | OpenAI sources |
|---|---|---|---|
ADM-G-256/ | 256×256 | 1.0 | 256x256_diffusion.pt + 256x256_classifier.pt |
ADM-G-512/ | 512×512 | 4.0 | 512x512_diffusion.pt + 512x512_classifier.pt |
Both resolutions use the class-conditional diffusion checkpoint plus the noisy classifier (not the 256 uncond variant).
Each variant keeps an id2label map directly in its own model_index.json (same style as DiT on the Hub). Runtime label resolution is English-only:
pipe.id2label — inspect id → English label correspondencepipe.labels — reverse map (English synonym → id), sorted for browsingpipe.get_label_ids("golden retriever")pipe(class_labels="golden retriever", ...)Chinese labels are still preserved in the main source repo under src/labels/id2label_cn.json for reference.

Settings used for this demo image: ADM-G-512, DDIMScheduler, num_inference_steps=50, guidance_scale=4.0, seed=42, class "golden retriever".
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
BiliSakura/ADM-diffusers/
├── README.md
├── ADM-G-256/
│ ├── pipeline.py
│ ├── model_index.json
│ ├── unet/
│ ├── classifier/
│ └── scheduler/
└── ADM-G-512/
├── pipeline.py
├── model_index.json
├── demo.png
├── unet/
├── classifier/
└── scheduler/
25 commits
1
stars
25
commits
1
repos using this model
1
linked in READMEs
May 29, 2026
updated
Self-contained OpenAI ADM-G checkpoints for Hugging Face diffusers. No external code repo is required — each subfolder ships its own pipeline.py, component modules, and weights.
This repo is derived from the development bundle in Visual-Generative-Foundation-Model-Collection, but inference only needs:
BiliSakura/ADM-diffusers)diffusers, torch, huggingface_hubThis Hugging Face repo hosts multiple self-contained checkpoints as subfolders. Each subfolder includes its own pipeline.py, model_index.json, weights, and component code (unet/, classifier/, scheduler/).
| Subfolder | Resolution | Guidance scale | OpenAI sources |
|---|---|---|---|
ADM-G-256/ | 256×256 | 1.0 | 256x256_diffusion.pt + 256x256_classifier.pt |
ADM-G-512/ | 512×512 | 4.0 | 512x512_diffusion.pt + 512x512_classifier.pt |
Both resolutions use the class-conditional diffusion checkpoint plus the noisy classifier (not the 256 uncond variant).
Each variant keeps an id2label map directly in its own model_index.json (same style as DiT on the Hub). Runtime label resolution is English-only:
pipe.id2label — inspect id → English label correspondencepipe.labels — reverse map (English synonym → id), sorted for browsingpipe.get_label_ids("golden retriever")pipe(class_labels="golden retriever", ...)Chinese labels are still preserved in the main source repo under src/labels/id2label_cn.json for reference.

Settings used for this demo image: ADM-G-512, DDIMScheduler, num_inference_steps=50, guidance_scale=4.0, seed=42, class "golden retriever".
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
BiliSakura/ADM-diffusers/
├── README.md
├── ADM-G-256/
│ ├── pipeline.py
│ ├── model_index.json
│ ├── unet/
│ ├── classifier/
│ └── scheduler/
└── ADM-G-512/
├── pipeline.py
├── model_index.json
├── demo.png
├── unet/
├── classifier/
└── scheduler/
25 commits