No360201
No360201
我用cascade训练了voc 07,map只有66%,在voc0712上的表现只有75%
when i use [openai/improved-diffusion](https://github.com/openai/improved-diffusion) train my data to get a diffusion model ,i get three .pt, which one is the diffusion model? when i load the model in [andreas128](https://github.com/andreas128)[RePaint](https://github.com/andreas128/RePaint) ,i...
i find the unet in https://github.com/openai/improved-diffusion is different from yours in the project ,can you help me? @andreas128 @freddy1020
Thanks for your excellent work. Do you plan to release the code? Maybe open inference code first
When I render models in batches, the results obtained in the later period are all blank, and many models will exceed the rendering image, is it a normalization error
how can you add 6 color image as condition of second stage diffusion? How do they control the corresponding output separately ?Thank you