4 Pull requests merged by 4 people

• [tests] fix audioldm2 for transformers main.

  #11522 merged May 8, 2025

• Conditionally import torchvision in Cosmos transformer

  #11524 merged May 8, 2025

• Add cross attention type for Sana-Sprint training in diffusers.

  #11514 merged May 8, 2025

• [LoRA] make lora alpha and dropout configurable

  #11467 merged May 8, 2025

3 Pull requests opened by 3 people

• [tests] add tests for framepack transformer model.

  #11520 opened May 8, 2025

• enable dit integration cases on xpu

  #11523 opened May 8, 2025

• RegionalPrompting: Inherit from Stable Diffusion

  #11525 opened May 8, 2025

2 Issues closed by 2 people

• Stable Virtual Camera

  #11151 closed May 8, 2025

• partial models spec in model_index.json

  #10413 closed May 8, 2025

1 Issue opened by 1 person

• Request support for MAGI-1

  #11519 opened May 8, 2025

24 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• LTX Video 0.9.7

  #11516 commented on May 8, 2025 • 6 new comments

• feat: pipeline-level quantization config

  #11130 commented on May 8, 2025 • 4 new comments

• Add VisualCloze

  #11377 commented on May 8, 2025 • 1 new comment

• [Feature] AutoModel can load components using model_index.json

  #11401 commented on May 8, 2025 • 1 new comment

• Add SkyReels-V2 pipelines

  #11518 commented on May 8, 2025 • 0 new comments

• Feat/multispectral dataloader 5ch

  #11517 commented on May 8, 2025 • 0 new comments

• [tests] add test for group_offloading with training.

  #11515 commented on May 8, 2025 • 0 new comments

• fix: remove `torch_dtype="auto"` option from docstrings

  #11513 commented on May 8, 2025 • 0 new comments

• [test_models_transformer_ltx.py] help us test torch.compile() for impactful models

  #11512 commented on May 8, 2025 • 0 new comments

• [tests] Changes to the `torch.compile()` CI and tests

  #11508 commented on May 8, 2025 • 0 new comments

• enable print_env on xpu

  #11507 commented on May 8, 2025 • 0 new comments

• enable 7 cases on XPU

  #11503 commented on May 8, 2025 • 0 new comments

• [Modular diffusers] more refactors

  #11484 commented on May 8, 2025 • 0 new comments

• [torch.compile] Make HiDream torch.compile ready

  #11477 commented on May 8, 2025 • 0 new comments

• [LoRA training] add aspect ratio bucketing

  #11438 commented on May 8, 2025 • 0 new comments

• [LoRA] parse metadata from LoRA and save metadata

  #11324 commented on May 8, 2025 • 0 new comments

• Bump jinja2 from 3.1.4 to 3.1.6 in /examples/server

  #11234 commented on May 8, 2025 • 0 new comments

• onnx export failure - timestep parameter with static value

  #11456 commented on May 8, 2025 • 0 new comments

• FlaxUNet2DConditionModel is not initialized with correct dtypes

  #11144 commented on May 8, 2025 • 0 new comments

• [tests] help us test `torch.compile()` for impactful models

  #11430 commented on May 8, 2025 • 0 new comments

• [core] refactor `attention_processor.py` the easy way

  #10022 commented on May 8, 2025 • 0 new comments

• [Models] handle initialization of new layers in a partially pre-trained model better

  #11279 commented on May 8, 2025 • 0 new comments

• [Quantization] Support TRT as a backend

  #11032 commented on May 8, 2025 • 0 new comments

• [Tests] fast tests single file checkpoints

  #6515 commented on May 8, 2025 • 0 new comments