Z Image Turbo.

It’s basically when you use a larger model to train a smaller one. You use a dataset of data generated by the teacher model and ground truth data to train the student model, and by some strange alchemy I don’t quite understand you get a much smaller model that resembles the teacher model.

It’s really hard training on a distilled model without breaking it, so people prefer models undistilled whenever possible. Without the teacher model, distilled models are basically cripple-ware.

Yeah, you can load Qwen Edit with Comfy UI. This tutorial for Comfy UI should help get you started.

Damn, that’s really cool.

Someone uploaded a Tchnicolor LoRA.

It seems to work. I’ve seen some in-progress LoRA samples floating around.

Yeah, if you’re using character LoRAs you’re probably going to need to use regional prompting to keep the concepts from bleeding into each other.

You might be thinking of a LoRA. LoRA are adapters you use with larger models to help it generate whatever concept you want.

You would probably need to use something like Visual Novel Character Creation Suite to generate a character and a dataset for LoRA training, and then train a LoRA for each character. LoRA are adapters you plug into larger models to help it generate whatever concept you want, in this case it would be a character. With a well-trained LoRA you shouldn’t have any problem with character consistency.

If you’re trying to get started with generating locally, here’s a tutorial for Comfy UI.

I salute that bust. 🫡

I think the noise is original. I’m pretty sure images aren’t compressed on Civitai.

It’s open source too.

Valid pun as long as you get creative with the kanji.

Too powerful for their own good. They would probably be driven out or exterminated.

I must admit, I didn’t try very hard on this title. Apologies.

Looks like WAI-illustrious-SDXL.

Whoops. Thanks for that.

Can you share any generation parameters for this? This community is for posting art made with Stable Diffusion and other open weight models. You shouldn’t post things made with ChatGPT, Midjourney, Nano Bannana or other closed Source models here.

That sounds pretty cool. I tried to find a photo of a real eclipse with the ocean in it online, but it’s way too hard to tell if they’re even real or if they’ve been heavily edited.

The background is pretty messed up IMO.