Warning: This is the 16-step model. The faster 8-step model can be found <a target="_blank" rel="ugc" href="https://civarchive.com/models/730604">HERE</a>[Note: Unzip the download to get the GGUF. Civit doesn't support it natively, hence this workaround]A merge of <a target="_blank" rel="ugc" href="https://civarchive.com/models/645943">FluxUnchained</a> and HyperSD LoRA from ByteDance - converted to GGUF. As a result, it can now generate artistic NSFW images in 16 steps while consuming very low VRAM. The Q_4_0 model consumes around 6.5 GB VRAM and takes around 3 min to generate a 1024x1024 image with 16 steps on my 1080ti. [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.]You can also combine it with other LoRAs to get the effect you want.<h2 id="advantages-cz8qx02q5">Advantages</h2><ul><li>Quality similar to the original FluxUnchained DEV model, while requiring only ~16 steps.</li><li>Better quality and expressivity than the 8-step HyperFlux Unchained in general.</li><li>For the same seed, the output image is pretty similar to the original DEV model, so you can use it to do quick searches and do a final generation with the dev model.</li><li>Sometimes you might even get better results than the DEV model due to serendipity :) .</li><li>Disadvantage: requires 16 steps</li></ul><h3 id="which-model-should-i-download-qrvs1ld71">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 16-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 Unchained 16-Steps (Flux Unchained + ByteDance HyperSD LoRA)

ggufHyperfluxUnchained16Steps_q40.zip

Files with SHA256: 8a2fa65201e6b9ad8217237d343aef2657037d71e52f945d9bbceefffa027b77