Neta Lumina Lightning LoRA

All cover images are raw output from the model, 1MP resolution, no upscale, no hands/faces inpainting fixes, even no negative prompt.

They said Lumina 2 is slow.

What about 2x faster 🚀.

This model is CFG distilled version of Neta Lumina, but trained as a LoRA natively, so you can apply it to any finetuned model.

The cost of CFG distillation is that you can't control negative prompt and CFG scale, they are inside the model. This is acceptable, we don't constantly change negative prompt and CFG scale anyways.

Unlike step distillation which is very aggressive, CFG distillation is simple and straightforward. So the quality penalty should be lesser.

I will try to release multiple sub versions, with different CFG (maybe different negative prompt too). So you can choose the CFG you want by choosing LoRA. Check "Update log" below for more details.

If you want to share your images, please post them to the main version page.

Currently support:

• NetaYume Lumina (NTYM)

How to use

Required settings to work:

• LoRA strength 1

• CFG scale 1 (This disables CFG, and negative prompt)

• Do not use cfg++ samplers, they do not work.

Recommended settings for better quality:

• Timesteps shift 3 (from node ModelSamplingAuraFlow)

• Steps > 20

Tips:

Use this ComfyUI plugin for more optimizations: https://civarchive.com/articles/22251

• 30% faster by using torch.compile.

• For older gpu (rtx 20xx and before), 3x faster by running in fp16 mode.

With proper setup Lumina 2 can be "almost" as fast as SDXL. "almost" means 80%.

If you really need to remove something using negative prompt and still want to generate faster. You can split your KSampler to two. First part (20% steps), normal settings with CFG. Second part (rest 80% steps), load this LoRA and set CFG to 1.

FAQ:

Does this LoRA support low steps?

No. This is not a step distillation. Step distillation is too much for me, as well as for the model.

License 

This model is released under Apache License 2.0.

Additional terms: Selling or monetizing models that merged this LoRA is prohibited.

Update logs

v0.2: init version

• v0.2: mimics the effect of CFG 3.5. Good for details.

• v0.2b: This version mimics the effect of CFG 5. Good for stability. Also smaller file size.

You have read this far, don't forget to leave a feedback in discussion. Don't write a review, Civitai review system is so hard to find and, most importantly, read...