Comfy-Org
/

Krea-2

Model card Files Files and versions

Resources

View closed (1)

Qwen 3 VL 4B Instruct or Thinking?

#8 opened about 18 hours ago by

Turbo vs Raw

#7 opened 2 days ago by

The sampling acceleration from nvfp4 quantization in Krea2 is not significant.

#6 opened 3 days ago by

Workflow LoRAs missing?

#5 opened 3 days ago by

text encoder gguf version quant 4 qwen 3 vl ?

#4 opened 4 days ago by

How is LoRa krea2_turbo_lora_rank_64_bf16.safetensors supposed to work, what's it good for?

#3 opened 4 days ago by

qwen3vl_4b_nvfp4?

#1 opened 5 days ago by