I took the Krea2 BF16 Safetensors from <a target="_blank" rel="ugc" href="https://huggingface.co/krea/Krea-2-Turbo/tree/main">https://huggingface.co/krea/Krea-2-Turbo/tree/main</a> and made two GGUF's Q8_0 and Q4_0. I tested both, and they worked with GGUF - I used this particular GGUF loader, but there are several out there for Krea, but this version I installed for Ideogram 4 GGUF and it just happens to work for Krea2 as well - <a target="_blank" rel="ugc" href="https://github.com/molbal/ComfyUI-GGUF">https://github.com/molbal/ComfyUI-GGUF</a>I do also have Krea2 RAW GGUF, but trust me it doesn't really make images, I only have it in case I can use it for Trained.

Krea2 Tubro Q8 from BF16

krea2TubroQ8FromBF16_krea2TubroQ40.gguf

Krea2 Tubro Q4_0

Krea2 Tubro Q8_0

I've done some work to convert Krea2 to GGUFs. It should come in handy for GPUs with &lt;8GB VRAM.Get the GGUF loader nodes from here: <a target="_blank" rel="ugc" href="https://github.com/molbal/ComfyUI-GGUF">https://github.com/molbal/ComfyUI-GGUF</a>Get the converted models from here: <a target="_blank" rel="ugc" href="https://huggingface.co/molbal/krea2-gguf">https://huggingface.co/molbal/krea2-gguf</a>Q4_0 uses 7573MB on my GPU, but GGUFs are generally easier to offload if you have less VRAM.

Files with SHA256: 3d28960e1f3385b27a224c6968a0acc02b07194758247e576ee0c5caaab4f1cf