refcontrol-FLUX.2-klein-reference-pose-lora

About

What refcontrol-FLUX.2-klein-reference-pose-lora is

RefControl FLUX.2 Klein 9B – Reference Pose LoRA 📝 Short description A LoRA for FLUX.2 Klein 9B Base that fuses a reference image (identity) with a pose control map (skeleton / keypoints). It preserves identity and style from the reference while following the body pose and structure from the pose map. Trigger phrase: apply pose from image 1 with reference from image 2 📊 Examples Each preview is a single combined image from ComfyUI: Pose → Reference → Result (left to right). 📖 Extended description This LoRA was primarily trained on humans, but it also works with stylized characters and some objects. Its main purpose is to preserve identity — facial features, hairstyle, clothing, or object details — from the reference image, while adapting the subject to the pose and skeleton structure defined by the control map. FLUX.2 Klein 9B Base already handles reference + pose transfer reasonably well with the right prompt alone. This LoRA builds on that capability — it improves consistency and better preserves character identity and pose fidelity than the base model without LoRA. Part of the RefControl family: reference + control fusion for consistent, controllable generation on FLUX.2 Klein 9B Base. ⚙️ How to use 1. Use the first image as the pose control map (skeleton / keypoints). 2. Use the second image as the reference (character, person, or object). 3. Add the trigger phrase apply pose from image 1 with reference from image 2 in your prompt. 4. Adjust LoRA weight (recommended 0.8–1.0) depending on how strongly you want to preserve identity. ComfyUI requirenments Pose extraction in the included workflow uses DWPose (via comfyuicontrolnetaux): https://github.com/Fannovel16/comfyuicontrolnetaux Base model Trained on and recommended with black-forest-labs/FLUX.2-klein-base-9B. The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps, guidancescale ~4.0). The LoRA also works with the 4-step distilled black-forest-labs/FLUX.2-klein-9B for faster inference (~4 steps, guidancescale ~1.0), but quality may be slightly lower — especially for identity and pose fidelity — compared to the Base model. ✅ Example prompt 🎯 What it does - Pres

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How image models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys refcontrol-flux-2-klein-reference-pose-lora for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (refcontrol-flux-2-klein-reference-pose-lora below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/images/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"refcontrol-flux-2-klein-reference-pose-lora","prompt":"a red bicycle","size":"1024x1024"}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More image models