vdaular/various-bucket/klein9 - Storage Bucket

FLUX.2 & Klein 9B RefMods (Reference Latent Adapters)

Open research, architecture documentation, and implementation repository for FLUX.2 & Klein 9B RefMods.

• Interactive Model Browser: https://huggingface.co/spaces/malcolmrey/browser (Search & visually explore 1,400+ characters, celebrities, and concepts)
• Model Weights Hub: https://huggingface.co/malcolmrey/klein9 (1,400+ pre-extracted .safetensors models)
• ComfyUI Custom Node: github.com/malcolmamal/ComfyUI-Flux2Klein9Mod
• CLI Generator & Batch Extractor: generate_flux2_klein9_refmod.py
• Official Workflows: workflows/ (workflow_klein9_refmod.json & workflow_klein9_refmod_lora.json)
• Target Models: FLUX.2, Klein 4B, Klein 8B, Klein 9B

---

📁 Repository Structure

klein9/
├── generate_flux2_klein9_refmod.py         <── CLI Generator & Mass Batch Extractor Tool
├── workflows/                              <── Mirrored Production Workflows
│   ├── workflow_klein9_refmod.json         <── Pure RefMod Text-to-Image Workflow
│   └── workflow_klein9_refmod_lora.json    <── Hybrid RefMod + LoRA Power Stack Workflow
├── docs/
│   ├── README.md                           <── Documentation Index
│   ├── FLUX2_KLEIN9_REFMODS_GUIDE.md       <── Complete Architecture, Extraction & Usage Guide
│   ├── VISUAL_BENCHMARKS_AND_COMPARISONS.md <── 5-Column Visual Benchmarks & Single Run Links
│   └── examples/                           <── Benchmark Grids & Single Run Artifacts (PNGs)
└── comfyui/
    └── custom_nodes/
        └── ComfyUI-Flux2Klein9Mod/         <── Full ComfyUI Custom Node Package

---

🚀 Quickstart

1. Install ComfyUI Custom Node

cd ComfyUI/custom_nodes
git clone https://github.com/malcolmamal/ComfyUI-Flux2Klein9Mod.git

2. Discover & Download RefMods

Search and find any character, celebrity, or concept .safetensors in the Malcolmrey Browser Space or directly on the Hugging Face Hub, then place the file into:

ComfyUI/models/refmods-klein9/

3. Load Ready-to-Use Workflows

Load either of the official JSON workflows located in workflows/:

• workflow_klein9_refmod.json: Pure RefMod Text-to-Image generation for FLUX.2 / Klein 9B.
• workflow_klein9_refmod_lora.json: Hybrid RefMod + LoRA Power Stack.

4. Extract Custom RefMods from Datasets

Use the included generator script generate_flux2_klein9_refmod.py:

# Extract single dataset by name or path
python generate_flux2_klein9_refmod.py C:/Development/ai-toolkit/datasets/your_character --token-budget 1024

# Preview media discovered without encoding
python generate_flux2_klein9_refmod.py your_character --dry-run

# Mass batch extract all datasets in directory
python generate_flux2_klein9_refmod.py --all --datasets-root C:/Development/ai-toolkit/datasets

---

📖 Complete Documentation & Visual Studies

• Interactive Model Browser: Live visual model finder with search and filter capabilities.
• FLUX.2 & Klein 9B RefMods Architecture Guide: Node specifications, graph wiring diagrams, token budget configurations, and extraction mechanics.
• Visual Benchmarks & 5-Column Comparison Studies: Side-by-side empirical visual comparisons (Pure LoRA vs 8-Raw Reference vs Pure RefMod vs Hybrid stack) with direct links to high-res single runs and model weights on Hugging Face.
• CLI Generator Script: Source code for dataset pre-encoding and batch processing.