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
HF Space to test this out?
#1
by tlennon-ie - opened
Thank you for your release, it looks promising and very suitable to how use cases are trending towards edit models but with the benefit of reasoning to help further direct the instruction in a way more suitable to how the model was trained.
Is it possible to have this on a space to test and demo?
Maybe @akhaliq could spin something up if there was enough interest :)