Model reference · open weights
Krea2 is an open-weight image model from thfzjj. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | thfzjj |
|---|---|
| Type | Image models |
| Task | Text→image |
| Runs with | diffusers |
| Released | 2026-08-02 |
| Popularity | 826 downloads / month |
| Licence | Commercial licence needed |
About
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.
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:
.weight keys with ndim >= 2 and element count > 1024) were quantized to torch.float8_e4m3fn.float32 / bfloat16).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.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 |
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.
Place these in your ComfyUI/models/ folder:
| File | Folder | Source |
|---|---|---|
krea2_turbo_fp8.safetensors | unet/ | AlperKTS/Krea2_FP8 ← You are here |
qwen3vl_4b_fp8_scaled.safetensors | text_encoders/ | Comfy-Org/Qwen3-VL |
qwen_image_vae.safetensors | vae/ | Comfy-Org/Qwen-Image_ComfyUI |
Drag workflows/Krea 2 simple workflow.json onto your ComfyUI canvas.
Turbo defaults: 8 steps, CFG 1.0, er_sde sampler, simple scheduler, 1280×720.
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.
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys thfzjj-krea2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (thfzjj-krea2 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"thfzjj-krea2","prompt":"a red bicycle","size":"1024x1024"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.