What's Changed

• Add temporal tiling support to video VAEs exposed through the VAE Decode (tiled) or VAE Encode (tiled) nodes, this makes 8GB vram GPUs viable for hunyuan video.
• Add PixArt model support by @city96 in https://github.com/comfyanonymous/ComfyUI/pull/6055
• Replace print with logging by @huchenlei in https://github.com/comfyanonymous/ComfyUI/pull/6138
• Adding upstream pytorch installation instruction for Intel GPUs to README.md by @qiacheng in https://github.com/comfyanonymous/ComfyUI/pull/6069
• remove minimum step count for AYS by @TechnoByteJS in https://github.com/comfyanonymous/ComfyUI/pull/6137
• fixed a bug in ldm/pixart/blocks.py by @zhangp365 in https://github.com/comfyanonymous/ComfyUI/pull/6158
• Add oneAPI device selector for xpu and some other changes. by @simonlui in https://github.com/comfyanonymous/ComfyUI/pull/6112
• [Bug] Use raw dir name to serve static web content by @huchenlei in https://github.com/comfyanonymous/ComfyUI/pull/6107
• Enable External Event Loop Integration for ComfyUI [refactor] by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/6114
• VAE calculations are now done in bf16 by default on Mac for lower memory usage.

New Contributors

• @qiacheng made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/6069
• @TechnoByteJS made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/6137
• @zhangp365 made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/6158

Full Changelog: https://github.com/comfyanonymous/ComfyUI/compare/v0.3.9...v0.3.10