Flux Turbo Lora加速模型_StarAi
Back

Flux Turbo Lora加速模型_StarAi

Other

Flux Turbo Lora加速模型_StarAi

可以配合lite超级量化模型双重加速（再提速23%，显存消耗8G左右）：

https://www.liblib.art/modelinfo/e145d0c1cf204822ba1a497edc01b1ba?mine



课件资料： https://ks8pfx9qgr.feishu.cn/docx/RS0PdamoIoU4z4xri45cORIwnjb



使用教程： https://www.bilibili.com/video/BV1PWyTY2Eb6/



由阿里妈妈创意团队开发的基于FLUX.1-dev模型的8步蒸馏版。

使用特殊设计的判别器来提高蒸馏质量。该模型可以用于T2I、Inpainting controlnet和其他FLUX相关模型。建议guidance_scale=3.5和lora_scale=1。

This model is sourced from an external transfer (transfer address: https://www.liblib.art/modelinfo/718ae87aceef4401bcf01172b9ea425e?from=search&versionUuid=604dd1da636e44d9a1a60a26b6dd5c3c ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request

blueeye

blueeye

Other

Model Information

Model Type：
LoRA
Basic Model：
FLUX.1 D

可以配合lite超级量化模型双重加速（再提速23%，显存消耗8G左右）：

https://www.liblib.art/modelinfo/e145d0c1cf204822ba1a497edc01b1ba?mine



课件资料： https://ks8pfx9qgr.feishu.cn/docx/RS0PdamoIoU4z4xri45cORIwnjb



使用教程： https://www.bilibili.com/video/BV1PWyTY2Eb6/



由阿里妈妈创意团队开发的基于FLUX.1-dev模型的8步蒸馏版。

使用特殊设计的判别器来提高蒸馏质量。该模型可以用于T2I、Inpainting controlnet和其他FLUX相关模型。建议guidance_scale=3.5和lora_scale=1。

This model is sourced from an external transfer (transfer address: https://www.liblib.art/modelinfo/718ae87aceef4401bcf01172b9ea425e?from=search&versionUuid=604dd1da636e44d9a1a60a26b6dd5c3c ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request