realrebelai/KREA-2_GGUFs

Krea 2 GGUF Sample Generations

KREA-2 GGUF Weights

Quantized GGUF weights for the Krea-2 Base model, optimized for low-VRAM and consumer hardware local workflows via ComfyUI.

🚀 Overview

Krea-2 is a Diffusion Transformer (DiT). Standard GGUF custom nodes will throw an Unexpected architecture type error natively. To run these weights, you must use our patched custom node fork.

📥 Downloading and Installation

1. Custom Node Requirements (Mandatory)

Standard loaders do not yet recognize krea2 architecture tags in GGUF metadata. Clone the following custom node into your ComfyUI/custom_nodes/ directory:

• Repository: RealRebelAI/ComfyUI-GGUF_KREA-2

2. Required Support Models

Place these base model files in your standard ComfyUI models/ directory:

• Text Encoder (CLIP): Qwen3-VL-4B-FP8-Scaled.safetensors (Load via CLIPLoader, ensuring Type is set to krea2)
• VAE: qwen_image_vae.safetensors (Load via VAELoader)

3. GGUF Weight Installation

1. Download your preferred quantization file (e.g., Krea-2-Base-Q4_K_S.gguf) from the Files and versions tab of this repository.
2. Place the downloaded .gguf file into your ComfyUI/models/unet/ (or equivalent GGUF directory) folder.
3. Load the model in ComfyUI using the UnetLoaderGGUF node.

⚙️ Workflow Notes

Ensure your conditioning setup is mapped appropriately to handle the stacked hidden state requirements of multimodal DiTs to avoid latent sequence mismatch errors.