Flux 2 Klein 9B Schematic LoRA
flux-non-commercial-license-v2.1
Modellquelle
- Art
- LoRA
- Dateigröße
- 158 MB
- Basismodell
- black-forest-labs/FLUX.2-klein-base-9B
- Version
- vflux2-klein-schematic-amodal-segmentation-lora
- Aktualisiert
- 14. Okt. 2026
- Downloads
- 0
- Quelle
- Hugging Face
Quellenbeschreibung
FLUX.2 Klein 9B Schematic LoRA
FLUX.2 Klein Schematic LoRA thumbnail
This project was inspired by Vision Banana, which treats tasks such as depth, normal, and segmentation as image editing.
I wanted to test whether a similar idea could work with FLUX.2 [klein] 9B base by using small task-specific LoRA training runs.
This repository contains six task-specific LoRAs:
- relative depth
- surface normal
- body pose
- full pose
- binary segmentation
- amodal segmentation
The outputs are RGB schematic images. The quality is not production-ready, and these LoRAs are not intended to replace dedicated CV models.
For more details about the experiment and dataset construction, see the blog post:
Files
| Task | LoRA |
|---|---|
| Relative depth | loras/flux2-klein-schematic-relative-depth-lora.safetensors |
| Surface normal | loras/flux2-klein-schematic-surface-normal-lora.safetensors |
| Body pose | loras/flux2-klein-schematic-body-pose-lora.safetensors |
| Full pose | loras/flux2-klein-schematic-full-pose-lora.safetensors |
| Binary segmentation | loras/flux2-klein-schematic-binary-segmentation-lora.safetensors |
| Amodal segmentation | loras/flux2-klein-schematic-amodal-segmentation-lora.safetensors |
Examples
Relative Depth
relative depth
Surface Normal
surface normal
Body Pose
body pose
Full Pose
full pose
Binary Segmentation
binary segmentation
Amodal Segmentation
amodal segmentation
Usage
Use the LoRA with FLUX.2 [klein] 9B base in an image-editing workflow.
These LoRAs were trained on the base model. They may not behave correctly with the distilled Klein models unless you also use an appropriate base-to-turbo / base-to-distilled compatibility LoRA.
Prompt Templates
Use simple command-style prompts.
Relative Depth
Generate a relative depth map of the input image.
Surface Normal
Generate a surface normal map of the input image.
Body Pose
Generate a body pose map of all visible people in the input image.
Full Pose
Generate a full pose map of all visible people in the input image.
Binary Segmentation
Generate a binary segmentation mask of [target] in the input image.
Amodal Segmentation
Generate an amodal segmentation mask of [target] in the input image.
ComfyUI Workflow
ComfyUI workflow screenshot
- JSON: workflow/flux2-klein-base-9b-image-edit.json
Notes
- This is not a drop-in replacement for dedicated preprocessors such as DWPose, Depth Anything, Lotus-2, or SAM.
- Pose is the least stable task. Small errors in color or skeleton topology are visually obvious.
- Segmentation can fail when the target description is ambiguous or when multiple similar objects are present.
- Amodal segmentation is especially experimental because the model must infer occluded parts.
- The dataset is small, so the behavior is limited and may vary across images.
Training Setup
- Base model:
black-forest-labs/FLUX.2-klein-base-9B - Training tool:
ai-toolkit - LoRA rank: linear
32/ conv16 - Optimizer:
adamw8bit - Learning rate:
5e-5 - Batch size:
4 - Dataset size:
1920image pairs across all tasks
Dataset
The training dataset is available here:
License
Please follow the license and usage terms of the base model:
black-forest-labs/FLUX.2-klein-base-9B.
This repository uses flux-non-commercial-license-v2.1.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 25. Sept.
Modellartefakte
1 Artefakt
Modellartefakte
1 Artefaktloras/flux2-klein-schematic-amodal-segmentation-lora.safetensors
safetensors · 158 MB · SHA-256 486e9fd65045…21b3 · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- license: other license_name: flux-non-commercial-license-v2.1 license_link: https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B/blob/main/LICENSE.md base_model: black-forest-labs/FLUX.2-klein-base-9B pipeline_tag: image-text-to-image language: - en tags: - lora - flux - flux2 - image-editing - depth - normal-map - pose - segmentation - comfyui --- # FLUX.2 Klein 9B Schematic LoRA  This project was inspired by [**Vision Banana**](https://vision-banana.github.io/), which treats tasks such as depth, normal, and segmentation as image editing. I wanted to test whether a similar idea could work with **FLUX.2 [klein] 9B base** by using small task-specific LoRA training runs. This repository contains six task-specific LoRAs: - relative depth - surface normal - body pose - full pose - binary segmentation - amodal segmentation The outputs are RGB schematic images. The quality is not production-ready, and these LoRAs are not intended to replace dedicated CV models. For more details about the experiment and dataset construction, see the blog post: - Blog: https://comfyui.nomadoor.net/en/notes/flux2-klein-schematic-lora/ ## Files | Task | LoRA | |---|---| | Relative depth | `loras/flux2-klein-schematic-relative-depth-lora.safetensors` | | Surface normal | `loras/flux2-klein-schematic-surface-normal-lora.safetensors` | | Body pose | `loras/flux2-klein-schematic-body-pose-lora.safetensors` | | Full pose | `loras/flux2-klein-schematic-full-pose-lora.safetensors` | | Binary segmentation | `loras/flux2-klein-schematic-binary-segmentation-lora.safetensors` | | Amodal segmentation | `loras/flux2-klein-schematic-amodal-segmentation-lora.safetensors` | ## Examples ### Relative Depth  ### Surface Normal  ### Body Pose  ### Full Pose  ### Binary Segmentation  ### Amodal Segmentation  ## Usage Use the LoRA with **FLUX.2 [klein] 9B base** in an image-editing workflow. These LoRAs were trained on the base model. They may not behave correctly with the distil...
Source context: 0 downloads · 84 likes · Pipeline image-text-to-image · Repo nomadoor/flux-2-klein-9B-schematic-lora
Source context: 0 downloads · 73 likes · Pipeline image-text-to-image · Repo nomadoor/flux-2-klein-9B-schematic-lora
