Hugging Face's logo

thedeoxen
/
refcontrol-FLUX.2-klein-9B-reference-pose-lora

Image-to-Image
Diffusers
flux
flux2
klein
pose
openpose
controlnet
refcontrol
img2img
image
editing
lora
Model card Files
xet
 Community
2
thedeoxen commited on
Commit
dcdb5ae
·
verified ·
1 Parent(s): 847ace3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -82,9 +82,11 @@ Pose extraction in the included workflow uses **DWPose** (via [comfyui_controlne
82
  https://github.com/Fannovel16/comfyui_controlnet_aux
83
 
84
  ### Base model
85
- Use with [`black-forest-labs/FLUX.2-klein-base-9B`](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B).
86
  The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps, `guidance_scale` ~4.0).
87
 
 
 
88
  ### ✅ Example prompt
89
 
90
  ```
@@ -117,6 +119,6 @@ apply pose from image 1 with reference from image 2
117
  ---
118
 
119
  ## 📦 Files
120
- - **Weights:** [`flux2_klein_9b_refcontrol_pose.safetensors`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/blob/main/flux2_klein_9b_refcontrol_pose.safetensors)
121
- - **ComfyUI workflow:** [`image_flux2_klein_image_edit_9b_refcontrol_pose.json`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/blob/main/image_flux2_klein_image_edit_9b_refcontrol_pose.json)
122
  - **Repo:** [thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora)
 
82
  https://github.com/Fannovel16/comfyui_controlnet_aux
83
 
84
  ### Base model
85
+ Trained on and recommended with [`black-forest-labs/FLUX.2-klein-base-9B`](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B).
86
  The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps, `guidance_scale` ~4.0).
87
 
88
+ The LoRA also works with the **4-step distilled** [`black-forest-labs/FLUX.2-klein-9B`](https://huggingface.co/black-forest-labs/FLUX.2-klein-9B) for faster inference (~4 steps, `guidance_scale` ~1.0), but **quality may be slightly lower** — especially for identity and pose fidelity — compared to the Base model.
89
+
90
  ### ✅ Example prompt
91
 
92
  ```
 
119
  ---
120
 
121
  ## 📦 Files
122
+ - **Weights:** [`refcontrol_v2_poses.safetensors`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/blob/main/refcontrol_v2_poses.safetensors)
123
+ - **ComfyUI workflow:** [`refcontrol_pose_flux_klein_9b.json`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/blob/main/refcontrol_pose_flux_klein_9b.json)
124
  - **Repo:** [thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora)