Image-to-Image
Diffusers
flux
flux2
klein
pose
openpose
controlnet
refcontrol
img2img
image
editing
lora
Instructions to use thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora") pipe = StableDiffusionControlNetPipeline.from_pretrained( "black-forest-labs/FLUX.2-klein-base-9B", controlnet=controlnet ) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Update README.md
Browse files
README.md
CHANGED
|
@@ -105,7 +105,6 @@ apply pose from image 1 with reference from image 2
|
|
| 105 |
## ⚡ Tips
|
| 106 |
- Best results when the pose map is not drastically different in body scale or framing from the reference.
|
| 107 |
- Combine with **text prompts** to refine background, lighting, or mood.
|
| 108 |
-
- Can be combined with other **RefControl** LoRAs (depth, lineart, canny) on compatible pipelines for multi-constraint generation.
|
| 109 |
- **DWPose** skeleton maps on a **black background** work well as control input.
|
| 110 |
|
| 111 |
---
|
|
|
|
| 105 |
## ⚡ Tips
|
| 106 |
- Best results when the pose map is not drastically different in body scale or framing from the reference.
|
| 107 |
- Combine with **text prompts** to refine background, lighting, or mood.
|
|
|
|
| 108 |
- **DWPose** skeleton maps on a **black background** work well as control input.
|
| 109 |
|
| 110 |
---
|