Hyper-SD is one of the new State-of-the-Art diffusion model acceleration techniques. In this repository, we release the models distilled from SDXL Base 1.0 and Stable-Diffusion v1-5Project Page: <a target="_blank" rel="ugc" href="https://hyper-sd.github.io/">https://hyper-sd.github.io/</a>Original Repo: <a target="_blank" rel="ugc" href="https://huggingface.co/ByteDance/Hyper-SD">https://huggingface.co/ByteDance/Hyper-SD</a>Original Paper: <a target="_blank" rel="ugc" href="https://arxiv.org/abs/2404.13686">https://arxiv.org/abs/2404.13686</a>

ByteDance Hyper-SD XL

Hyper-SDXL-2steps-lora.safetensors

Hyper-SDXL - 2 Steps

Hyper-SDXL - 8 Steps CFG

Hyper-SDXL - 8 Steps

Hyper-SDXL - 4 Steps

Hyper-SDXL - 1 Step

Hyper-SDXL-2steps-lora can quickly generate images without the need to frequently try various mapping parameters, which I personally like.Here is a shared download available.Select 'Extended Models' in the webui and forgeui settings, and scroll down to' Keep all models displayed on Lora page '(Otherwise, models that are incompatible with the currently loaded Stable Diffusion model version will be hidden) ", check the box. You can find 'Hyper SDXL-2steps lora' in Lora.

Hyper-SDXL-2steps-lora

Hyper-SDXL-2steps-lora can quickly generate images without the need to frequently try various mapping parameters, which I personally like.Here is a shared download available.

Files with SHA256: 69b25c0187ced301c3603c599c0bc509ac99b8ac34db89a2aecc3d5f77a35187