RuWANG

**Describe the bug** A clear and concise description of what the bug is. Thanks for this great work, it really very good. But when I try to use Google Cloud...

when excute: best_params_use, best_clusters_use, trials_use = utils.bayesian_search(embeddings_st1, space=hspace, label_lower=int(label_lower), label_upper=int(label_upper), max_evals=int(max_evals)) TypeError: 'numpy.float64' object cannot be interpreted as an integer. I didn't modify any part of this notebook

Integrate CutMix into the unet_discriminator_mha which is original UNet.

https://arxiv.org/abs/2002.12655 This PR implements the pixel et bottleneck discriminator. example : ``` python3 train.py --dataroot /path/to/horse2zebra --checkpoints_dir /path/to/checkpoints --name horse2zebra --config_json examples/example_gan_horse2zebra.json --D_netDs projected_d unet_128_d basic ```

WIP: video_unet_generator_attn

7

- [x] step0 Get a similar architecture of UNet(ResBlock+AttentionBlock) in joliGEN comparable as in AnimateDiff(ResBlock+TransformerBlock+MotionModule) - [x] step1 Modify ResBlock to process 5D tensor image for input and output -...

feat(ml): add lambda

1

add function lambda into cm_gan_model - [x] inference - [x] unit tests - [x] documentation The training works with the following command line > python3 train.py \ --dataroot /data1/juliew/dataset/noglasses2glasses_ffhq \...

add G_prompt for cut_turbo for unaligned dataset and works for batch_size larger than 1 - [x] inference - [x] unit tests - [x] documentation The training works with the following...