All credit belongs to the original model author. License is the same as the original model.
Source du modèle
Description de la source
Converted from https://huggingface.co/Comfy-Org/Krea-2/tree/main/diffusion_models
All credit belongs to the original model author. License is the same as the original model.
int8convt qwen3vl text encoder: link .
About mixed precision and txtfusion layers:
This quantized ckpt uses mixed precision. Which keeps important layers in high precision. Thus it's a little bit larger than other fully quantized ckpt.
All txtfusion layers are in high precision. You don't needs to worry the precision when applying "Refusal-Reduction" LoRA (or whatever new LoRAs that try to nuke the txtfusion layers and the safety filter).
Sources
1 sourceArtefacts du modèle
2 artefactskrea2W4a8_turboFp8Nvfp4.safetensors
safetensors · FP8 · FULL · 14,0 GB · SHA-256 4b1f5d99aad8…7bfe · Civitai
Téléchargerkrea2W4a8_turboFp8Nvfp4.safetensors
safetensors · NF4 · FULL · 9,37 GB · SHA-256 dbd638588bce…4a5f · Civitai
TéléchargerExtraits de sources
3 extraitsSource context: 1001 downloads · Type Checkpoint · Base model Krea 2
Scaled fp8 and nvfp4 are deprecated.
Use int8convrot or w4a8 instead.
Source context: 793 downloads · Type Checkpoint · Base model Krea 2
Source context: 740 downloads · Type Checkpoint · Base model Krea 2