ExponentialML

Are there parameters for making the source facial details stronger?

91

First of all, great work. Are there parameters that can keep more of the details from the source image, or is this something that needs to be trained on? For...

This is less of an issue and more of a discussion. First of all, great work. I've trained a few models and it works great, but was wondering if a...

Clarity On Training.

2

Hello. Again, great work! I'm a little confused about the training part. You say: ``` To train a model run: CUDA_VISIBLE_DEVICES=0 python run.py --config config/dataset_name.yaml --device_ids 0 ``` Then there's...

There isn't any link to the "CelebAudio Dataset"

1

"We provide our CelebAudio Dataset at link." There isn't any link to your dataset.

Implement with Stable Diffusion repositories

4

Hello, thanks for the implementation! It works very well. As a suggestion, it may be helpful to provide code that works with the broader Github community. While the Diffusers library...

Feature: Invoke Emotion With Two Audio Sources

5

Hello, thanks for the awesome project! This is very fun to mess around with. One thing I've been having fun with doing is mix and mashing voices together. I've noticed...

Allow Lora models to be injected by monkey patching via script

3

**WHAT** Lora models should be able to be injected via a script instead of creating an entirely new model. **HOW** Unless I'm wrong here, the Lora weights are applied to...

- [x] Allow for multiple cached latents. - [x] Update param to allow shuffling. - [x] Automatically cast to float32. Uses more memory, but encourages better stability. - [x] Allow...