Flux2-Dev FP8 & GGUF

Update your ComfyUI [Github] to 0.3.72 ( cd comfyui-directory -> terminal -> git pull -> restart ComfyUi)

10GB VRAM + 64GB RAM => Yes (CLIP device: CPU + Diffusion Model Loader KJ (Triton & dtype fp8_e4m3fn )

Recommended resolutions:

(Flux2 is flexible and can handle any aspect ratio up to 4MP total)

• Square: 1024×1024, 2048×2048

• Landscape: 2048×1024, 3072×1536

• Portrait: 1024×2048, 1536×3072

• Ultra-Wide: 4096×1024

[ 408x2816, 1408x2688, 1536x2688, 1536x2560, 1664x2432, 1664x2304, 1792x2304, 1792x2176, 1920x2176, 1920x2048, 2048x2048, 2048x1920, 2176x1920, 2176x1792, 2304x1792, 2304x1664, 2432x1664, 2560x1536, 2560x1408, 2688x1536, 2688x1408, 2816x1408, 2816x1280, 2944x1408, 3072x1280, 3200x1280, 3328x1152, 3456x1152 ]

FLUX.2 [dev] is a 32 billion parameter rectified flow transformer capable of generating, editing and combining images based on text instructions. More info

Key Features

1. State of the art in open text-to-image generation, single-reference editing and multi-reference editing.

2. No need for finetuning: character, object and style reference without additional training in one model.

3. Trained using guidance distillation, making FLUX.2 [dev] more efficient.

4. Open weights to drive new scientific research, and empower artists to develop innovative workflows.

5. Generated outputs can be used for personal, scientific, and commercial purposes

These models are redistributed here for the sake of convenience.