AlperKTS / Krea2_FP8

Krea 2 OSS - Optimized FP8 Weights (Turbo)

This repository provides an optimized FP8 (float8_e4m3fn) weight-only quantized version of the newly released Krea 2 OSS (Turbo) transformer.

This optimization reduces the model size from the original 24.76 GiB (BF16) down to 12.01 GiB , making it highly accessible and runnable on standard consumer hardware (such as 16GB and 24GB GPUs) without sacrificing output quality.

⚠️ Licensing & Disclaimer

• Original Model Creators : All credit goes to KREA.ai for the original research, architecture, and weights.
• License : This model is subject to the KREA 2 License Agreement . Please read and comply with the official license terms before using these weights: KREA 2 Licensing Terms .
• Purpose : This repository is a community-contributed utility. It does not claim ownership of the original model or architecture. Its sole purpose is to provide optimized, consumer-hardware-friendly weights for the open-source community.

🛠️ Quantization Details (Quality-First FP8)

Unlike generic global quantization scripts that aggressively convert every parameter (which often degrades generation details or introduces NaN/promotion calculation errors in neural networks), this model was quantized using a selective weight-only strategy :

1. Targeted Quantization : Only 2D floating-point weight matrices ( .weight keys with ndim >= 2 and element count > 1024 ) were quantized to torch.float8_e4m3fn .
2. Preserved Precision :
   • All 1D vectors, biases, and normalization scales are kept in their native high-precision ( float32 / bfloat16 ).
   • Highly sensitive projection/modulation layers (such as LastLayer.modulation.lin vectors) are completely preserved in high-precision. This prevents typical mathematical promotion bugs (such as BFloat16 and Float8 promotion issues in PyTorch) and retains original output fidelity.
3. Weight Comparison :
   • Tensors Quantized to FP8 : 266 tensors.
   • Tensors Kept in Native Precision : 166 tensors.
   • Size Reduction : 24.76 GiB ➔ 12.01 GiB (~51.5% VRAM / disk savings!).

🖼️ Sample Generations

Below are official sample outputs from the original Krea 2 OSS Turbo model (generated with the same BF16 weights this FP8 conversion is based on):

3D	Anime	Beach
Blocks	Cel	Dog
Face	Flowers	Fox
Future	Goldface	Jester
Mouse	Red	Ride
Sailor	Statue	Takeoff
Tree	Wind

🚀 How to Use in ComfyUI (Native — 0.25.0+)

ComfyUI 0.25.0+ has built-in Krea2 support . No custom nodes needed.
Drop the workflow JSON into ComfyUI and drag it to the canvas.

1. Download Required Files

Place these in your ComfyUI/models/ folder:

2. Load the Workflow

Drag workflows/Krea 2 simple workflow.json onto your ComfyUI canvas.

3. Queue & Generate!

Turbo defaults: 8 steps, CFG 1.0, er_sde sampler, simple scheduler, 1280×720.

🤝 Acknowledgements

Special thanks to the KREA.ai team for releasing Krea 2 to the open-source community. For any commercial licensing inquiries or details about the model, please visit krea.ai .