nanonomad

My voice model wasnt great for this, so it shouldnt be considered ideal performance by any means.

Heres Bill Gates rapping: https://youtu.be/1ztm7aBssgA

"

Compositional generation. Our method can compose multiple diffusion models during inference and generate images containing all the concepts described in the inputs without further training"

Mostly LAION 5B, IIRC. Keep safe mode on unless you want to be inundated with 90s era pornog.

Browsing the dataset for inference terms can help build better prompts. For example, juicy seems to be a particularly weird term involving grapefruits index fingers and japanese people. so id probably use a synonym instead

Itll comfortably run on 6gb now. gtx1600 series cards need to run in full precision mode to produce output. The HLKY fork has improved the Gradio GUI and integrated realesrgan and gfpgan for those with beefier cards.

Someone else also figured out how to load and run it all on a CPU, so pretty much anyone can in theory run the model now.

There is an elaborate Colab notebook linked in the HLKY repo that seems to get more point and click user friendly every time i look at it. I think it even launches the gradio webui so you can use the Colab instance with a webui remotely.

Look into nicotinic acid, a form of niacin. The "flushing" one. If you supplement with it start slow, get used to the burning sensation. It goes away after a few times.

Avoid biologics unless you absolutely have to