Dhruv Nair
Dhruv Nair
# What does this PR do? Add support for converting safetensors format AnimateDiff checkpoints to diffusers. Fixes # (issue) #7751 ## Before submitting - [ ] This PR fixes a...
# What does this PR do? Adds workflow similar to [transformers](https://github.com/huggingface/transformers/actions/runs/8829908548/workflow) that let's us SSH into the runners to debug issues. Fixes # (issue) ## Before submitting - [ ]...
# What does this PR do? Single file loading is still far from ideal. We should aim to align the behaviour as close to from_pretrained as possible (with the goal...
# What does this PR do? Made some updates to the original PR: #5853 Doc pages that are not tested include - Training examples (these should be tested in with...
# What does this PR do? One potential cause for timeout issues in the Pipeline tests could be that the shared memory size for the container is set to 16GB....
**Is your feature request related to a problem? Please describe.** We currently support passing in callbacks to pipelines in order to manipulate/customise aspects of the diffusion process. It would be...
# What does this PR do? There are a couple of differences between transformers workflows and ours. e.g. We don't have a clone our repo in our docker image. Update...
# What does this PR do? These tests download the `v1-5-pruned-emaonly.ckpt` for SD 1.5, however we've updated our `torch.load` to default to use the `weights_only=True` which is causing issues with...
# What does this PR do? Running the failing tests that have cache issues on our SSH runner which uses `/mnt/cache/.cache/huggingface:/mnt/cache/` and the tests are passing. Updating the cache here...
Residual noise from DDIM and issues with GIF export are affecting the quality of AnimateDiff results. Update docs based on info from this issue: https://github.com/huggingface/diffusers/issues/7548