Instructions to use lilylilith/AnyPose with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lilylilith/AnyPose 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("Qwen/Qwen-Image-Edit-2511", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lilylilith/AnyPose") 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
- Local Apps Settings
- Draw Things
Prompts and tips
#11
by Safeswimming69 - opened
I had better luck with this prompt using your lora: "change the actions and poses in Image 1 to match those in Image 2. Remove the background of image 2, and replace it with the background of image 1."
For the use case of pose transfer from image 2 to image 1 I also;
remove background of image 2 and relace with black
resize with padding image 1 to match dimensions of image 2
I also always use 8 step lightning lora (2511) and always cfg 1.5