Mohammed Innat

Still open for any suggestion and recommendation. ( no github-action bot please, 🔕 )

@patrickvonplaten https://twitter.com/matthieurouif/status/1589539286814461953

@patrickvonplaten Could you please open it?

Candidates: https://huggingface.co/docs/diffusers/using-diffusers/controlling_generation

Probably this can be gained from recent strategies, i.e. controlnet.

CC @patrickvonplaten Subject-driven Text-to-Image Generation via Apprenticeship Learning https://arxiv.org/abs/2304.00186# 

cc @sachinprasadhs This should be reopened.

@mattdangerw > Something that goes directly keras.ops to the onnx format? Sounds good. Here is [jax2xla](https://github.com/google/jax/blob/main/examples/onnx2xla.py), a numpy backedn onnx interpreter, [google/jaxonnxruntime](https://github.com/google/jaxonnxruntime). > And how would that compare to going...

@divyashreepathihalli @tirthasheshpatel This PR is ready to take some initial feedback. I have some query. - What does `kaggle_handle` mean? (A weight file or folder! If so, how [this config](https://github.com/keras-team/keras-cv/blob/9dd547a725c081db0264023717f43d14301ea3d2/keras_cv/models/backbones/efficientnet_v2/efficientnet_v2_backbone_presets.py#L17-L27)...

- [x] mixed precision - OK - [x] keras-cv-video-swin VS torchvision-vidoe-swin - [notebook](https://www.kaggle.com/code/ipythonx/video-swin-transformer-kerascv-and-torchvision/notebook) - [x] keras-cv-video-swin - single gpu | [notebook](https://www.kaggle.com/code/ipythonx/kerascv-video-swin-sample-training/notebook) - [x] with pure torch, - [x] with tensorflow...