Highlights
- Pro
Block or Report
Block or report patrickvonplaten
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePopular repositories
-
Wav2Vec2_PyCTCDecode Public
Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode
-
-
-
-
2,084 contributions in the last year
Less
More
Contribution activity
August 2022
Created 1 repository
- patrickvonplaten/stable-diffusion Jupyter Notebook
Created a pull request in huggingface/huggingface_hub that received 15 comments
[Repository] Add better error message
This PR simply adds a better error message for the following use case: from huggingface_hub import Repository repo = Repository(local_dir="data", c…
+10
−0
•
15
comments
Opened 16 other pull requests in 5 repositories
huggingface/diffusers
6
merged
1
closed
huggingface/transformers
2
open
2
merged
sanchit-gandhi/seq2seq-speech
2
open
huggingface/blog
2
merged
CompVis/stable-diffusion
1
merged
Reviewed 36 pull requests in 6 repositories
huggingface/diffusers
21 pull requests
-
Style the
scriptsdirectory - Reproducible images by supplying latents to pipeline
- add inpainting example script
- [Clean up] Clean unused code
- split tests_modeling_utils
- Update README for 0.2.3 release
- [Do not merge] Script to compare safety checkers
- Pipeline to device
- Add safety module
- [StableDiffusionPipeline] use default params in __call__
- fix test_from_pretrained_hub_pass_model
- Add K-LMS scheduler from k-diffusion
- [Half precision] Make sure half-precision is correct
- [PNDM] Stable diffusion
- allow custom height, width in StableDiffusionPipeline
- add tests for stable diffusion pipeline
- Stable diffusion pipeline
- [PNDM in LDM pipeline] use inspect in pipeline instead of unused kwargs
- allow pndm scheduler to be used with ldm pipeline
- Add an alternative Karras et al. stochastic scheduler for VE models
- add attention up/down blocks for VAE
huggingface/transformers
11 pull requests
- Determine framework automatically before ONNX export
- Mask t5 relative position bias then head pruned
- BLOOM Flax
- Add ONNX support for Longformer
- [Wav2vec2 + LM Test] Improve wav2vec2 with lm tests and make torch version dependent for now
- Type cast before normalize
- [Hotfix] pin detectron2 5aeb252 to avoid test fix
- Add hallucination filter
- [LayoutLMv3] Add TensorFlow implementation
- PEGASUS-X
-
Generate: validate
model_kwargson FLAX (and catch typos in generate arguments)
sanchit-gandhi/seq2seq-speech
1 pull request
huggingface/blog
1 pull request
CompVis/stable-diffusion
1 pull request
huggingface/huggingface_hub
1 pull request
Created an issue in huggingface/diffusers that received 8 comments
Allow non-default schedulers to be easily swapped into DiffusionPipeline classes
Is your feature request related to a problem? Please describe. By default the stable diffusion pipeline uses the PNDM scheduler, but one could easi…
8
comments





