continue revolution

fp8 in this fork should be set via adding command line argument `--unet-in-fp8-e4m3fn`

```python def mm_cn_forward(forward_fn, cn_type, *args): controls = [] for i in range(0, args[0].shape[0], 2 * self.ad_params.batch_size): current_args = (arg[i:i + 2 * self.ad_params.batch_size].to(get_torch_device()) if type(arg) == torch.Tensor else arg for...

also the cond hint itself can sometimes oom for some people and we can't load them all to gpu sometime/ if u have a better way to handle it then...

i also need to modify https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/main/extensions-builtin/sd_forge_controlnet/scripts/controlnet.py#L317 because I want to cap the index to not exceed the max of images across each batch folder. It is easy for me to...

thanks. i will modify this pr and ping u once it's done

check out [my extension](https://github.com/continue-revolution/sd-webui-segment-anything). It now supports GSA

I will almost certainly support it as soon as possible in my A1111 extension https://github.com/continue-revolution/sd-webui-animatediff/ since in the paper it mentioned that it used AnimateDiff, if the release date is...

These Chinese big tech companies normally have a long process of review before open-source is approved internally. Wait at least one more month. Alibaba's review process is at least 2...

Please see my pull request https://github.com/tqchen/ffi-navigator/pull/52 I met the same problem and resolved in this way.

This is SAM's error, and I am unfortunately unable to help you because I do not have access to multiple GPU. Please post your question at SAM repository: https://github.com/facebookresearch/segment-anything