GGUF: HyperFlux Unchained 16-Steps (Flux Unchained + ByteDance HyperSD LoRA)

Warning: This is the 16-step model. The faster 8-step model can be found HERE

[Note: Unzip the download to get the GGUF. Civit doesn't support it natively, hence this workaround]

A merge of FluxUnchained 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 https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1050 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.

Advantages

• Quality similar to the original FluxUnchained DEV model, while requiring only ~16 steps.

• Better quality and expressivity than the 8-step HyperFlux Unchained in general.

• 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.

• Sometimes you might even get better results than the DEV model due to serendipity :) .

• Disadvantage: requires 16 steps

Which model should I download?

[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 < Q4_1 < Q5_0 < Q5_1 < Q8_0.

• Q4_0 and Q4_1 should fit in 8 GB VRAM

• Q5_0 and Q5_1 should fit in 11 GB VRAM

• Q8_0 if you have more!

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 https://huggingface.co/ByteDance/Hyper-SD/tree/main