Total runs:
11.6K
Run Growth:
8.8K
Growth Rate:
75.53%
Sponsored by
Agentkit
thedeoxen / refcontrol-FLUX.2-klein-4B-reference-depth-lora
Model's Last Updated: May 28 2026
image-to-image
Introduction of refcontrol-FLUX.2-klein-4B-reference-depth-lora
Model Details of refcontrol-FLUX.2-klein-4B-reference-depth-lora
RefControl FLUX.2 Klein 4B - Reference Depth LoRA
📝 Short description
A LoRA for
FLUX.2 Klein 4B Base
that fuses a
reference image
(left) with a
depth map
(right).
It preserves
identity and style
from the reference while following the
pose and structure
from the depth map.
Trigger word:
refcontrol
📊 Examples
| Reference | Depth | Result |
|---|---|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
📖 Extended description
This LoRA was primarily trained on
humans
, but it also works with
objects
and stylized characters.
Its main purpose is to
preserve identity
- facial features, clothing, style, or object characteristics - from the reference image, while adapting the subject to the
pose and composition
defined by the depth map.
Part of the RefControl family: reference + control fusion for consistent, controllable generation on FLUX.2 Klein 4B Base .
⚙️ How to use
- Use first image as depth reference, second image input.
-
Add the trigger word
refcontrolin your prompt. - Adjust LoRA weight (recommended 0.8-1.0 ) depending on how strongly you want to preserve identity.
ComfyUI requirenments
For extracting depth you need to install nodes with depth estimation in workflow used:
https://github.com/Fannovel16/comfyui_controlnet_aux
Base model
Use with
black-forest-labs/FLUX.2-klein-base-4B
.
The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps,
guidance_scale
~4.0).
✅ Example prompt
refcontrol
🎯 What it does
- Preserves character or object identity across generations.
- Embeds the subject into a new pose or scene defined by the depth map.
- Works best when the depth map has similar proportions and scale to the reference.
⚡ Tips
- Best results when the depth map is not drastically different in object scale from the reference.
- Combine with text prompts to refine background, lighting, or mood.
- Can be combined with other RefControl LoRAs (pose, lineart, canny) on compatible pipelines for multi-constraint generation.
📌 Use cases
- Human portraits in different poses.
- Consistent character design across multiple scenes.
- Object transformations (cars, furniture, props) with depth-guided placement.
- Storyboarding, comics, or animation frame generation.
📦 Files
Runs of thedeoxen refcontrol-FLUX.2-klein-4B-reference-depth-lora on huggingface.co
1.0K
Total runs
0
24-hour runs
40
3-day runs
92
7-day runs
92
30-day runs
More Information About refcontrol-FLUX.2-klein-4B-reference-depth-lora huggingface.co Model
Url of refcontrol-FLUX.2-klein-4B-reference-depth-lora
refcontrol-FLUX.2-klein-4B-reference-depth-lora huggingface.co Url
Provider of refcontrol-FLUX.2-klein-4B-reference-depth-lora huggingface.co
Other API from thedeoxen
Updated:August 19 2026
Total runs:
11.4K
Run Growth:
1.3K
Growth Rate:
11.92%
Total runs:
8.2K
Run Growth:
1.1K
Growth Rate:
13.22%
Total runs:
1.2K
Run Growth:
103
Growth Rate:
8.82%
Total runs:
823
Run Growth:
165
Growth Rate:
20.05%
Total runs:
519
Run Growth:
-1.0K
Growth Rate:
-193.45%
Total runs:
439
Run Growth:
-290
Growth Rate:
-66.06%
Total runs:
276
Run Growth:
-102
Growth Rate:
-36.96%
Total runs:
63
Run Growth:
22
Growth Rate:
34.92%
Total runs:
30
Run Growth:
9
Growth Rate:
30.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%