--- title: Krea2_FP8 canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Krea2_FP8" md_url: "https://www.modelscope.cn/models/AI-ModelScope/Krea2_FP8.md" repository: AI-ModelScope/Krea2_FP8 last_updated: 2026-06-23 license: other pipeline_tag: text-to-image-synthesis tasks: - text-to-image-synthesis model_type: - krea2 parameters: 12.9B tensor_type: - F8_E4M3 - F32 library_name: - lora - diffusers - safetensors - pytorch frameworks: - pytorch downloads: 703 stars: 3 tags: - text-to-image - image-generation - dit - fp8 - comfyui - diffusers - krea - krea2 --- # Krea2_FP8 > Krea2_FP8 - AI-ModelScope 在 ModelScope 开源的模型。Krea 2 OSS - Optimized FP8 Weights (Turbo) AI-ModelScope/Krea2_FP8 是 ModelScope 魔搭社区上的 12.9B 参数text-to-image-synthesis模型，采用 other 许可。 - **Repository**: AI-ModelScope/Krea2_FP8 - **License**: other - **Tasks**: text-to-image-synthesis - **Parameters**: 12.9B - **Tags**: text-to-image, image-generation, dit, fp8, comfyui, diffusers, krea, krea2 - **Downloads**: 703 - **Stars**: 3 - **Last updated**: 2026-06-23 Source: https://www.modelscope.cn/models/AI-ModelScope/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](https://www.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](https://www.krea.ai/krea-2-licensing). - **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](assets/samples/3d.png) | ![anime](assets/samples/anime.png) | ![beach](assets/samples/beach.png) | | **3D** | **Anime** | **Beach** | | ![blocks](assets/samples/blocks.png) | ![cel](assets/samples/cel.png) | ![dog](assets/samples/dog.png) | | **Blocks** | **Cel** | **Dog** | | ![face](assets/samples/face.png) | ![flowers](assets/samples/flowers.png) | ![fox](assets/samples/fox.png) | | **Face** | **Flowers** | **Fox** | | ![future](assets/samples/future.png) | ![goldface](assets/samples/goldface.png) | ![jester](assets/samples/jester.png) | | **Future** | **Goldface** | **Jester** | | ![mouse](assets/samples/mouse.png) | ![red](assets/samples/red.png) | ![ride](assets/samples/ride.png) | | **Mouse** | **Red** | **Ride** | | ![sailor](assets/samples/sailor.png) | ![statue](assets/samples/statue.png) | ![takeoff](assets/samples/takeoff.png) | | **Sailor** | **Statue** | **Takeoff** | | ![tree](assets/samples/tree.png) | ![wind](assets/samples/wind.png) | | | **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: | File | Folder | Source | |------|--------|--------| | `krea2_turbo_fp8.safetensors` | `unet/` | [AlperKTS/Krea2_FP8](https://huggingface.co/AlperKTS/Krea2_FP8) ← You are here | | `qwen3vl_4b_fp8_scaled.safetensors` | `text_encoders/` | [Comfy-Org/Qwen3-VL](https://huggingface.co/Comfy-Org/Qwen3-VL/tree/main/text_encoders) | | `qwen_image_vae.safetensors` | `vae/` | [Comfy-Org/Qwen-Image_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae) | ### 2. Load the Workflow Drag [`workflows/Krea 2 simple workflow.json`](workflows/Krea%202%20simple%20workflow.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](https://www.krea.ai).