Image-to-Image
Diffusers
English
lora
flux
flux.2
flux.2-klein
character-swap
face-swap
occlusion-handling
photorealistic
Instructions to use nhathoangfoto/Flux.2-Klein-9B-Mannequin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nhathoangfoto/Flux.2-Klein-9B-Mannequin 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("black-forest-labs/FLUX.2-klein-base-9B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("nhathoangfoto/Flux.2-Klein-9B-Mannequin") prompt = "jhuangswap — cycle through: character source → target body → final output" 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
- Local Apps Settings
- Draw Things
LoRA looks like it's invisible
#3
by StableDiffusion69 - opened
No matter what I do, it always generates some generic mannequin. It's like the image isn't picked up and read. I have no idea on how to solve this. I use a simple FLUX2 wf, there is nothing to it.
Any hints?
StableDiffusion69 changed discussion status to closed