Tensor.Art
Create

Qwen Image 2512 Turbo 2-8 Steps LoRA - bf16 - 2steps

Qwen Image 2512 Turbo 2-8 Steps LoRA

LORA
Reprint

Updated:

bf16 - 2steps
bf16 4-8 steps v2.0

Credit: https://huggingface.co/Wuli-art/Qwen-Image-2512-Turbo-LoRA

Recommended settings:

"Works at Low CFG values 1-2; fries the image at Qwen Image 2512's default CFG of 4".

Thanks to @Dumplings

Qwen-Image-2512-Turbo-LoRA is a 4 or 8-steps turbo LoRA for Qwen Image 2512 trained by Wuli Team. This LoRA matches the original model's ouput quality but is over 20x faster⚡️, 2x from CFG-distillation and others from reduced number of inference steps.

Version Detail

Qwen-Image

Project Permissions

Model reprinted from : https://huggingface.co/Wuli-art/Qwen-Image-2512-Turbo-LoRA

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts