w-e-w
w-e-w
- https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/15564 - https://github.com/numz/sd-wav2lip-uhq/pull/127
as I don't have these browser installed I haven't confirmed if the ever exist but if it does I believe this is more of a Upstream gradio issue
gradio 4.x upgread is WIP https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14184 this might be fix by gradio 4
sorry for the delay I was on vacation and then I became very busy (still very busy now) --- I tested the extension and it works very nicely well ......
post your API code form my testing when scheduler is not set the vaule us `None` by default ```py WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"...
I believe the intentions of the clip developers for putting their models under `~.cache/clip` is so that the clip modules can be shared across multiple software without re-downloading
modle loading is a mess in webui I suggest you just settle with `Maximum number of checkpoints loaded at the same time` to `1` and `Only keep one model on...
these can aslo help https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings --nowebui --skip-load-model-at-start
`sd_models.model_data.sd_model` yeah I think that's pretty much the place you want to look however if you also used `Checkpoints to cache in RAM > 0` then I think you also...