[Note: Unzip the download to get the GGUF. Civit doesn't support it natively, hence this workaround]A merge of Flux.D with the 8-step HyperSD LoRA from ByteDance - turned into GGUF. As a result, you get an ultra-memory efficient and fast DEV (CFG sensitive) model that generates fully denoised images with just 8 steps while consuming ~6.2 GB VRAM (for the Q4_0 quant).It can be used in ComfyUI with this <a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF">custom node</a> or with Forge UI. See <a target="_blank" rel="ugc" href="https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1050">https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1050</a> to learn more about Forge UI GGUF support and also where to download the VAE, clip_l and t5xxl models.<h2 id="advantages-over-fastflux-and-other-dev-schnell-merges-7pkvqk12q">Advantages Over <a rel="ugc" href="https://civarchive.com/models/657607/gguf-fastflux-flux1-schnell-merged-with-flux1-dev">FastFlux</a> and Other Dev-Schnell Merges</h2><ul><li>Much better quality: you get much better quality and expressiveness at 8 steps compared to Schnell models like FastFlux</li><li>CFG/Guidance Sensitivity: Since this is a DEV model, unlike the Hybrid models, you get full (distilled) CFG sensitivity - i.e., you can control prompt sensitivity vs. creativity and softness vs. saturation.</li><li>Fully compatible with Dev LoRAs, better than the compatibility of Schnell models.</li><li>The only disadvantage: needs 8-step for best quality. But then, you'd probably try at least 8 steps for best results with Schnell anyway.</li></ul><h3 id="which-model-should-i-download-8rv9m6hy1">Which model should I download?</h3>[Current situation: Using the updated Forge UI and Comfy UI (GGUF node) I can run Q8_0 on my 11GB 1080ti.]Download the one that fits in your VRAM. The additional inference cost is quite small if the model fits in the GPU. Size order is Q4_0 &lt; Q4_1 &lt; Q5_0 &lt; Q5_1 &lt; Q8_0.<ul><li>Q4_0 and Q4_1 should fit in 8 GB VRAM</li><li>Q5_0 and Q5_1 should fit in 11 GB VRAM</li><li>Q8_0 if you have more!</li></ul>Note: With CPU offloading, you will be able to run a model even if doesn't fit in your VRAM.All the license terms associated with Flux.1 Dev apply.PS: Credit goes to ByteDance for the HyperSD Flux 8-steps LoRA which can be found at <a target="_blank" rel="ugc" href="https://huggingface.co/ByteDance/Hyper-SD/tree/main">https://huggingface.co/ByteDance/Hyper-SD/tree/main</a>

GGUF: HyperFlux 8-Steps (Flux.1 Dev + ByteDance HyperSD LoRA)

ggufHyperflux8StepsFlux1_q40.zip

HyperFlux 8-Steps (Flux.1 Dev + ByteDance HyperSD 

Files with SHA256: e5804eb20b4621e6835faed256b2326b53639eb0820a7b40fcee9d45dac82176