import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-9B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("nappa114514/Flux_Klein_illustration_style_transfer")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]illustration style transfer
This is a model that transfers artistic style from a reference image.
It has primarily been trained on transferring styles between illustrations and is not very good at converting between realistic and illustrative styles.
| Example 1 |
|---|
 |
| Example 2 |
|---|
 |
for Flux Klein 9B/4B
cifk4002.safetensors for 4B
cifk9001.safetensors for 9B
Trigger
Transfer the style of image2 to image1
If the background changes, please add the following words:keep background of image1
Workflow
styletransfer_fk4.json for ComfyUI
- Downloads last month
- 113
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nappa114514/Flux_Klein_illustration_style_transfer
Base model
black-forest-labs/FLUX.2-klein-9B