YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Krea 2 All-In-One (ComfyUI)
Single-file ComfyUI checkpoint packing the full Krea 2 stack: diffusion model + abliterated Qwen3-VL-4B text encoder + Qwen-Image VAE. Drop it in models/checkpoints/ and load it with a standard CheckpointLoaderSimple โ no separate CLIP/VAE nodes needed.
Contents
| Component | Source file |
|---|---|
| Diffusion model | krea2Turbo18For_v2_3128505.safetensors (Krea 2 Turbo) |
| Text encoder | Huihui-Qwen3-VL-4B-Instruct-abliterated-fp8_scaled.safetensors |
| VAE | qwen_image_vae.safetensors (Qwen-Image) |
Key layout matches ComfyUI's native AIO format (model.diffusion_model.*, text_encoders.qwen3vl_4b.transformer.*, vae.*), verified against the Krea2 config in comfy/supported_models.py.
Rebuilding from components
See pack_krea2_aio.py โ it remaps and merges the three component files into this checkpoint.
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support