Shanghua Gao
Shanghua Gao
Currently, we are using SD 2.1 as the base model, so we are using 512x512 for training. Do you mean to train a model with resolution 1024 x 768? I...
It should be able to work with 1024x768. Maybe there are some settings that make this resolution not working. I will check it and let you know.
That would be great!!!Thanks!!!!
I can train one if you need it. Is there a reason for this? Doest SD1.5 has some advantage over SD2.0?
okay, then I will train one very soon.
hi, I have trained new sam condition models based on sd15 and sd21. These models are trained with more images and longer iterations. https://github.com/sail-sg/EditAnything#model-zoo
We provide the gradio UI. But I have no server with GUI now, so I didn't test the gradio UI. Please open an issue if you find bugs.
Yes, the label color is randomly generated. We didn't use the random color for training, it's just for visualization.
We train it from the stable diffusion2 using the SAM mask as the condition. Not pretrained canny or scribble model is used. Do you think using these models as the...
res2net_v1b is one version of the Res2Net we provided, and you can use our code and pretrained model for your research work.