HappyYang comments

Results 7 comments of


                                            HappyYang

why not super resolution models, such as SRGAN, ESRGAN

Thanks

why not super resolution models, such as SRGAN, ESRGAN

here I have another question, can I incorporate the super resolution model into 'mmdetection',

Expected tensor for argument #1 'input' to have the same type as tensor for argument #2 'rois'; but type torch.cuda.HalfTensor does not equal torch.cuda.FloatTensor

I also meet this question

Will the MLSD models available for SDXL be made public?

I also need the normal version for SDXL

Training step

> Thanks for your attention! You can refer to our paper to find the details😁 sorry, i don't find the training step

I meet a problem that 'ImportError: cannot import name 'DualLearning' from 'imed_vision.models.segmentation' (/workspace/workspace/imed_vision-main/scripts/imed_vision/models/segmentation/__init__.py)'

Tensor size mismatch for non pow of 2 sized image, SD3ControlNetModel

> The mentioned issues with VAE tiling are due to: [vae/config.json](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers/blob/main/vae/config.json) > > Having: > > ``` > "use_post_quant_conv": false, > "use_quant_conv": false > ``` > > Which causes the...