|
Download README.md from Zabin/Qwen_Image_2.1_Turbo_8Steps: direct link, hf CLI and curl.
- Browser
- Download file 1.26 kB
-
https://huggingface.co/Zabin/Qwen_Image_2.1_Turbo_8Steps/resolve/main/README.md
- Command line
-
hf download hf://Zabin/Qwen_Image_2.1_Turbo_8Steps/README.md
-
curl -L -o README.md https://huggingface.co/Zabin/Qwen_Image_2.1_Turbo_8Steps/resolve/main/README.md
1.26 kB
metadata
license: other
license_name: qwen-research
license_link: LICENSE
base_model:
- Qwen/Qwen-Image-2.1
language:
- en
This repository contains:
- QwenImage_2.1_turbo_8Steps_bf16.safetensors -> (Qwen 2.1 bf16) merged with Turbo LoRas to give a completed image in 8 Steps.
- QwenImage_2.1_turbo_8Step_Int8_Convrot.safetensors -> Int8 Convrot version. Gives a completed image in 8 Steps.
- qwen_image2.1_5Steps_int8_convrot_v3.safetensors -> Produces and Edits Image in 5 Steps.
Recipe
Loras From: https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo
- v0.21 LoRA: Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r128.safetensors -> 0.75
- v0.1 LoRA: Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors -> 0.15
- https://huggingface.co/chriswritescode/Turbo8-LoRA-Qwen-Image-2.1 -> 0.2
- Merged with Qwen Image 2.1 Bf16 Version. Then exported.
Caveats
- Can produce anatomical errors.
- Can produce grid noise.

