Image-to-Image
Diffusers
Safetensors
MiniMax H3
English
character-swap
image-editing
lora-merge
ml-intern
Instructions to use akhaliq/MiniMax-H3-Image-Character-Swap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use akhaliq/MiniMax-H3-Image-Character-Swap 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("akhaliq/MiniMax-H3-Image-Character-Swap", 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] - Notebooks
- Google Colab
- Kaggle
tested with lora 1.5
#3
by Leon1000 - opened
Leon1000 changed discussion title from tested with loar 1.5 to tested with lora 1.5
Can you share your workflow? The effect of using Lora is not very good, and the editing results are unstable
Can you share your workflow? The effect of using Lora is not very good, and the editing results are unstable
I just used the default workflow and a lora ( I am not sure if the lora works ), make sure at least 4mp. Maybe you can try prompt, for example:
<image 1> is a woman and a man. the woman handstand and kick the man.
<image 2> is a woman.
<image 3> is a man.
target image: replace the woman in <image 1> with <image 2>, replace the man in <image 1> with <image 3>, change the background to a subway underground, dim light.
realistic.

