Instructions to use ProCreations/Image-2.1-Turbo-Calibrated-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ProCreations/Image-2.1-Turbo-Calibrated-FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ProCreations/Image-2.1-Turbo-Calibrated-FP8", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Release calibrated Image 2.1 Turbo FP8 transformer, accelerated SM120 runtime, quality evidence and real-time demo
ffc54ec verified Download source/verify_base.py from ProCreations/Image-2.1-Turbo-Calibrated-FP8: direct link, hf CLI and curl.
- Browser
- Download file 1.21 kB
-
https://huggingface.co/ProCreations/Image-2.1-Turbo-Calibrated-FP8/resolve/main/source/verify_base.py
- Command line
-
hf download hf://ProCreations/Image-2.1-Turbo-Calibrated-FP8/source/verify_base.py
-
curl -L -o verify_base.py https://huggingface.co/ProCreations/Image-2.1-Turbo-Calibrated-FP8/resolve/main/source/verify_base.py
1.21 kB
| """Verify the local Qwen-Image-2.1-Turbo snapshot against upstream sizes and LFS SHA-256 (assets excluded).""" | |
| import hashlib, json, time | |
| from huggingface_hub import HfApi | |
| from common import BASE, BASE_REPO, BASE_REVISION, ROOT | |
| info = HfApi().model_info(BASE_REPO, revision=BASE_REVISION, files_metadata=True) | |
| rows = [] | |
| for f in info.siblings: | |
| if f.rfilename.startswith('assets/'): | |
| continue | |
| p = BASE / f.rfilename | |
| assert p.exists(), f.rfilename | |
| h = hashlib.sha256() | |
| with p.open('rb') as s: | |
| while b := s.read(8 << 20): h.update(b) | |
| digest = h.hexdigest() | |
| if f.size is not None: assert p.stat().st_size == f.size, f.rfilename | |
| if f.lfs: assert digest == f.lfs.sha256, (f.rfilename, digest) | |
| rows.append({'file': f.rfilename, 'bytes': p.stat().st_size, 'sha256': digest, 'upstream_lfs_sha256_matched': bool(f.lfs)}) | |
| receipt = {'model': info.id, 'revision': info.sha, 'files': rows, 'total_bytes': sum(r['bytes'] for r in rows), | |
| 'excluded': 'assets/* preview images (not needed for inference)', 'verified_at': time.time()} | |
| (ROOT / 'base_integrity.json').write_text(json.dumps(receipt, indent=2)) | |
| print('BASE_VERIFIED', len(rows), receipt['total_bytes']) | |