Youngon
Youngon
求拉 w1018485761
have you solved it？or any instruction found?
me neither.
> can you show us your script with more details? Is this issue solved, wait your reply ASAP
> @wangmiaowei can you re-try text-image using this branch? https://github.com/hpcaitech/ColossalAI/tree/feature/stable-diffusion/applications/stable-diffusion/text_img2img we are updating to newer version. If you have some question, you can contact me @tiandiao123 does this error be...
有更通用（丰富）的中英文数据集吗
> This is a very cool project! I think this approach will also allow to train diffusion models on a large amount of unlabeled data, and then just connect the...
I have changed the pipeline and can do "txt+img -> img" work, but the model doesn't work well, so looking up to the upgrade from janus.
I checked my pipeline, if masking the image embeddings, it can generate image according to the prompt; while I add unstanding part, can successfully unstand the content of input image....