Zhijie Lin

i also encounter this problem

> At least give some scripts. Maybe try this repo: https://github.com/sail-sg/BindDiffusion

> I am also interested in this. Any news? Also, how can you retrieve an image based on image and audio/text? I am referring to the embedding space arithmetic examples...

> In[ CMIN_moment_retrieval/dataloaders/clip_loader.py line 66 ](https://github.com/ChenyunWu/CMIN_moment_retrieval/blob/df44a230a0cd83d9ab3e282601da60cbca56a102/dataloaders/clip_loader.py#L66) > `if label[1] == video.shape[0] - 1:` > Shouldn't it be: > `if label[1] == ori_video_len:`? > Since you changed the `video` and its...

> 昨天就差验证码输入的慢了点，今天进去就无了 有人一起来研究他的api么？我这已经抓到一些api了 可以跳过两步操作直接到确定页面 我也研究了一些了，可以一起研究？

A original script can be found in [sam_train_sd21.py](https://github.com/sail-sg/EditAnything/blob/main/sam_train_sd21.py). Also, the training pipeline for diffuser should be similar to https://huggingface.co/docs/diffusers/training/controlnet.

- controlnet_conditioning_scale_map is a 2D tensor map for pixel-wise control_scale. - alpha_weight is the mixing strength with original image during denoising. - alignment_ratio is the control the number of steps...

@gasvn @MahdiMohseni0033 Should be fixed right now. > https://github.com/sail-sg/EditAnything/blob/f123c475c261c63651f7d63262570dd575ce8f3f/sam2edit_lora.py#L602-L631