diffusers

diffusers copied to clipboard

Adding DreamBooth paper super resolution fine tuning

1

I'm currently experimenting with the dreambooth training script, and while the results are very impressive, I think it is missing the super resolution fine tuning phase? In the dreambooth paper...

alicranck

Updates Image to Image Inpainting community pipeline README

1

- Corrects example usage (see #1114 , thanks @socathie !) - Adds example inputs and results

vvvm23

[Examples] Update `unconditional_image_generation/train_unconditional.py` to include Weights and Biases Logger

4

Unborked PR of #1209 > The current example uses Tensorboard as the only available logger. Adding Weights and Biases allows us to interact with the model metrics, alongside the saved...

ash0ts

Latent upscaler

3

WIP. The upscaler model does not predict the noise, but the denoised image. Therefore it needs to use schedulers that support `predict_epsilon=False`. In addition, [the noise schedule is configured from...

pcuenca

### Describe the bug `trained_betas` is a numpy array, and it cannot be serialized to JSON. This makes it currently impossible to save the configuration of a custom scheduler that...

pcuenca

Any guidance on creating smaller images? 256x256 or 384x384?

3

**Is your feature request related to a problem? Please describe.** I’m looking for ways to speed the process and save memory **Describe the solution you'd like** I wondered if it...

MatthewWaller

Not able to load after a successful login

4

### Describe the bug I am trying to load diffusers either from a remote. Remote huggingface diffusers is not accessible after a successful login ### Reproduction ```shell (pytorch)$ huggingface-cli login...

DSLituiev

Safetensors support

2

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] Provide a way to...

Narsil

Help replicating imagen

6

Hello, I'm trying to replicate imagen using the diffusers library, so far I've trained the 64x64 unet, next I have to train the 256x256 model. My question is, what is...

thedarkzeno

Add experimental Heun scheduler

1

Without duplicating the sigmas and timesteps (reference: #1336) ➕ No duplication of sigmas and timesteps. Does not require ugly function `index_for_timestep` (or confusing oneliner repeated twice in the code) ➖...

pcuenca