search

AIGODLIKE / ComfyUI-ToonCrafter

This project is used to enable ToonCrafter to be used in ComfyUI.
Apache License 2.0
332 stars 11 forks source link

added half precision weights link to the model prepare section #7

Closed FizzleDorf closed 6 months ago

FizzleDorf commented 6 months ago

as the title says. the fp16 weights require much less VRAM and won't run out of memory like the full weights do on a 4090.

FizzleDorf commented 6 months ago

the model isn't being applied yet since it's always looking for the full weights. I'll add a model select instead so it should be a lot better. I might be training a 1024 model as well so the ability to select models would be ideal to implement early

KarryCharon commented 6 months ago

the model isn't being applied yet since it's always looking for the full weights. I'll add a model select instead so it should be a lot better. I might be training a 1024 model as well so the ability to select models would be ideal to implement early

Model selecttion is finished! We are testing fp16 version now.

FizzleDorf commented 6 months ago

It is possible to make it work on a 3080 10GB. With Xformers you will be able to fit a 512x240 generation into VRAM. Should be around two minutes to do a ~16 frame animation. also, you can run in fp8 to save ~2gb of VRAM on top of that.