Huanran Chen
Huanran Chen
It seems impossible to do this in RGB space. Have someone succeeded to do this?
similar problem!
same problem!
Hi! This is because we only use the VisionEncoder of Blip2. Blip2 consists of a vision encoder and a text decoder, the prompt will be only used by text decoder....
I'm sorry; you are right. It's my fault; it should have included some text prompts. Perhaps this is one of the reasons the "Text Description Attack" didn't perform well. However,...
> Hi, I'm interested in your work, but I have some questions about that. > > 1. So for "Text Description Attack", we should include text prompts, right? > 2....
> @dongyp13 @huanranchen hey This is Monika. I really appreciate the work you guys did. I need your help, I am trying to implement/replicate this project as my semester long...
Is there any torch checkpoints and implementations of CIFAR10 consistency models?
> You can also use `.shard()` and call `to_parquet()` on each shard in the meantime: > > num_shards = 128 > output_path_template = "output_dir/{index:05d}.parquet" > for index in range(num_shards): >...
Thanks a lot! This error occurs since dt is too small. By setting "min_step": 0.01, it works! > There is a min_step argument if you use any RK adaptive-step solver...