diffusers

diffusers copied to clipboard

Adding additional input channels to model after intialization

2

Have scoured the docs for an answer to this, to no avail. Is it possible to add additional input channels to a model after initializing it using `.from_pretrained`. For example...

BenjaminIrwin

Unable to correctly install dependencies for Dreambooth example on GCP user or managed notebooks

3

### Describe the bug I am attempting to simply run the [Dreambooth training example](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth) on a GCP Vertex AI workbench notebook. I have tried their managed notebook and user-managed notebooks...

DevonPeroutky

How to check a checkpoints output quality?

2

If I use --checkpointing_steps for dreambooth training, is there a way to check the output/quality of those checkpoints? Can I automatically create sample images at each checkpoint? Since the description...

djdookie

FID on CIFAR10 does not match literature

4

### Describe the bug I used the unconditional training script from examples to train a model on CIFAR10, using default parameters (except using 1024 steps). After around 250k updates (batch...

lukovnikov

How to use a specific model from huggingface or Google Drive to train the images / How to load model locally?

2

I would like to train subjects in a specific model, how can I use it here instead of the original stable diffusion model 1.4, 1.5, 2.0, ecc

dvelm

question about attention block

1

why we use torch.baddbmm to do query @ key? https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention.py#L640

xiaohu2015

getting stuck at dreambooth training examples

8

I am trying to reproduce the 'Dog toy example' in https://github.com/huggingface/diffusers/tree/main/examples/dreambooth but I am getting stuck at https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py#L675 forever. Do you know how to fix it? I have followed through...

zihao12

Getting Error: signal: floating point exception (core dumped) when changing the scheduler

1

I am trying to change the scheduler of my dreambooth model in the inference call. But I am getting the following error when I do so: ``` Error: signal: floating...

geekyayush

[Flax] Stateless schedulers, fixes and refactors

4

Hi, here some fixes and improvements for the Flax schedulers. Let me know what you think! Sorry that its a huge PR with a single commit :sweat_smile: ### Refactor schedulers...

skirsten

[MPS] Some of the `DPTForDepthEstimation` ops are not supported on MPS

2

To reproduce, remove the mps skips in `StableDiffusiondepth2imgPipelineFastTests`: https://github.com/huggingface/diffusers/blob/cd91fc06fe9513864fca6a57953ca85a7ae7836e/tests/pipelines/stable_diffusion_2/test_stable_diffusion_depth.py#L154 This is probably solvable on the `transformers` side, but opening an issue here too to keep track of the testing :)

anton-l