Instructions to use stepfun-ai/Step1X-Edit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stepfun-ai/Step1X-Edit with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-image" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-image", model="stepfun-ai/Step1X-Edit")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("stepfun-ai/Step1X-Edit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
18 days ago
-
Add VDEBench evaluation results
Verified signatureHi 👋 this PR adds this model's **[VDEBench](https://huggingface.co/datasets/hongzhuyi/VDEBench)** scores to `.eval_results/`, so they show up on the model page and on the VDEBench leaderboard. VDEBench evaluates instruction-guided editing of dense English/Chinese document pages (3,506 examples). Each score is the equally weighted mean of IoU, CDM, BLEU-4 and TEDS (0–1, higher is better): | Task | Score | |---|---:| | `local` (edited region, headline) | 0.482 | | `global` (full page) | 0.580 | Scores come from the VDEBench paper ([arXiv:2602.00122v4](https://arxiv.org/abs/2602.00122v4), Table 2), and the VDEBench authors confirmed both the values and the evaluated checkpoint ([discussion](https://huggingface.co/datasets/hongzhuyi/VDEBench/discussions/2)). While this PR is open the scores appear as community-provided; merging it makes them official, and closing it removes them. Docs: https://huggingface.co/docs/hub/eval-results · https://huggingface.co/docs/hub/leaderboard-data-guid…878676b
-
Upload step1x-edit-v1p1-official.safetensors with huggingface_hub
Verified signature752c0bc
-
update eval res
zzlongjuanfeng0204499 -
Delete results_show.png
Verified signature1f102cb -
Delete logo.png
Verified signaturee6a97df -
Delete image_edit_demo.gif
Verified signature4d0c81a -
Delete eval_res_en.png
Verified signature4051de2 -
Delete arch.png
Verified signature5c4b2fa -
Upload folder using huggingface_hub
Verified signatureeb93947
-
Delete step1x-edit-lora256-alpha128-fix-hand.safetensors
Verified signature0620ddd -
Upload folder using huggingface_hub
Verified signatureba776b9 -
Upload folder using huggingface_hub
Verified signature0385d13 -
Fix corrupted config.json (#7)
Verified signature- Fix corrupted config.json (fefdf67353c7d8a4f5fcb6b42a238e5e3ebecbef) Co-authored-by: FlareAI <SkyBlockSquadd@users.noreply.huggingface.co>c733a44
-
Upload config.json with huggingface_hub
Verified signature30771b3
-
Delete assets/.DS_Store
Verified signature35ecb62 -
Delete .DS_Store
Verified signaturef22e9ea -
Upload LICENSE with huggingface_hub
Verified signature91717ba -
Upload README.md with huggingface_hub
Verified signature0ac9e65
-
Add paper abstract and link to Github repository (#2)
Verified signature- Add paper abstract and link to Github repository (76a3858f0542137c071c3b01add084725fc143de) Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>8e1568d
-
Upload README.md with huggingface_hub
Verified signature99a965e -
Upload README.md with huggingface_hub
Verified signature2588e10 -
Upload folder using huggingface_hub
Verified signatureda51930 -
Upload README.md with huggingface_hub
Verified signature60e45a6 -
Upload README.md with huggingface_hub
Verified signature8af445b -
Upload README.md with huggingface_hub
Verified signatureac70c04
-
Upload folder using huggingface_hub
Verified signature1708284 -
Upload folder using huggingface_hub
Verified signature27b2012
-
Update README.md
Verified signature5e77802 -
Upload folder using huggingface_hub
Verified signature7fd55c2 -
Upload folder using huggingface_hub
Verified signature806cb2e -
Upload folder using huggingface_hub
Verified signature6508c4f -
initial commit
Verified signature6899f79