Instructions to use stepfun-ai/Step1X-Edit-v1p2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stepfun-ai/Step1X-Edit-v1p2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stepfun-ai/Step1X-Edit-v1p2", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
Add VDEBench evaluation results
#2
by hongzhuyi - opened
This PR adds Step1X-Edit-v1p2 results for VDEBench, evaluated on all 3,506 examples of dense English and Chinese document editing.
| Task | Score ↑ |
|---|---|
| Local (edited region, headline) | 0.638 |
| Global (full page) | 0.751 |
Each score is the equally weighted mean of IoU, CDM, BLEU-4 and TEDS on a 0–1 scale. The result file links to the full metric record from the VDEBench team.