This is an SVDQuant int4 conversion of my <a target="_blank" rel="ugc" href="https://civarchive.com/models/699688?modelVersionId=1693152">CreArt-Ultimate Hyper Flux.1_Dev model</a> for <a target="_blank" rel="ugc" href="https://github.com/mit-han-lab/nunchaku">Nunchaku</a>.It was converted with <a target="_blank" rel="ugc" href="https://github.com/mit-han-lab/deepcompressor">Deepcompressor</a> at <a target="_blank" rel="ugc" href="https://www.runpod.io/">Runpod</a> using an A40.It increases rendering speed by 3x.You can use it with 10 steps without having to use Lora Turbo.But 12 steps and turbo lora with strenght 0.2 give best result.Work only on comfyui with the <a target="_blank" rel="ugc" href="https://github.com/mit-han-lab/ComfyUI-nunchaku">Nunchaku nodes</a>This int4 version does not work with rtx 5000

SVDQuant-int4-CreArt_Ultimate for Nunchaku 0.2.0 And 0.3.0

svdq-int4-CreArt_Ultimate Version merged for nunchaku 0.3.0

Files with SHA256: 7d7d46c11583960f91b07c8210c977a4e9e27745272035b92b989edfb37a62ab