diffusers
diffusers copied to clipboard
huggingface
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Added support for CIFAR10 in training example and automatic resolution selection + printing of param counts
**Is your feature request related to a problem? Please describe.** Trying to train Stable Diffusion on your local box using the Dreambooth method causes out-of-memory issues on an RTX 3090....
The new fine-tuned inpaint pipeline in 0.6.0 release is very good, but its UNet architecture is different from original pipeline. I think the inpaint pipeline in 0.5.1 release has some...
It's really difficult to test stable diffusion due to the following: - 1. **Continous output**: Diffusion models take float values as input and output float values. This is different from...
The dreambooth setup can be very useful for more general finetuning as show by the community with examples such as style fine tuning. https://twitter.com/rainisto/status/1584112851446542336 I've been using an approach adding...
I fine tuned a stable diffusion model and saved the check point which is ~14G. And then I used the script in this repo [convert_original_stable_diffusion_to_diffusers.py](https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py) to convert it to diffusers,...
### Describe the bug Whenever you run the convert_original_stable_diffusion_to_diffusers.py in google colab it results in the error cannot import name 'StableDiffusionSafetyChecker' from 'diffusers.pipelines.stable_diffusion ### Reproduction run the code on google...
For https://lablab.ai/t/stable-diffusion-img2img , it seems that only [LMSDiscreteScheduler](https://huggingface.co/docs/diffusers/api/schedulers#diffusers.LMSDiscreteScheduler) works well in [generating different variations of the pictures sketches](https://colab.research.google.com/drive/1LMDWu5TUUGjjTnis7wkYP1TY77DxaRa7#scrollTo=0O0Iy1zK0q-8&line=4&uniqifier=1), that is my observation so far Besides, it seems that both `RePaintScheduler`...
I am trying to generate synthetic images starting from a black and white 1-channel training data set using the DDPMPipeline. This is my UNet2D model ``` model = UNet2DModel( sample_size=config.image_size,...
**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 [...] **Describe the solution you'd...
Metadata
Owner
Metadata
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.