ComfyUI Files

What's Changed

• Portable with cu128 isn't useful anymore. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12666
• feat(ace-step): add ACE-Step 1.5 lycoris key alias mapping for LoKR #… by @fappaz in https://github.com/Comfy-Org/ComfyUI/pull/12665
• bug_report template: Push harder for logs by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12657
• feat: Support SDPose-OOD by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12661
• Enable Pytorch Attention for gfx950 by @vickytsang in https://github.com/Comfy-Org/ComfyUI/pull/12641
• Fix GLSL node requiring all input images to have same dimensions by @pythongosssss in https://github.com/Comfy-Org/ComfyUI/pull/12673
• feat: add ResolutionSelector node for aspect ratio presets by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12199
• Class WanVAE, def encode, feat_map is using self.decoder instead of self.encoder by @ReinerBforartists in https://github.com/Comfy-Org/ComfyUI/pull/12682
• ops: implement lora requanting for non QuantizedTensor fp8 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12668
• Limit overlap in image tile and combine nodes to prevent issues. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12688
• Native LongCat-Image implementation by @Talmaj in https://github.com/Comfy-Org/ComfyUI/pull/12597
• PyOpenGL-accelerate is not necessary. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12692
• refactor: use enum members as ASPECT_RATIOS dict keys by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12689
• fix(ace15): handle missing lm_metadata in memory estimation during ch… by @fappaz in https://github.com/Comfy-Org/ComfyUI/pull/12686
• feat: Support SCAIL WanVideo model by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12614
• Disable dynamic_vram when weight hooks applied by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12653
• cli_args: Default comfy to DynamicVram mode by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12658
• Move parsing of requirements logic to function. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12701
• Disable dynamic vram on wsl. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12706
• refactor: rename Mahiro CFG to Similarity-Adaptive Guidance by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12172
• feat: add text preview support to jobs API by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12169
• fix: handle substep sigmas in context window set_step by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/12719
• comfy aimdo 0.2.3 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12720
• Make --disable-smart-memory disable dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12722
• model_mangament: make dynamic --disable-smart-memory work by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12724
• comfy aimdo 0.2.4 - Fix unaligned allocator sizes by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12727
• feat(api-nodes): allow to use "IMAGE+TEXT" in NanoBanana2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/12729
• Update workflow templates to v0.9.5 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/12732
• Support loading zeta chroma weights properly. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12734
• Feat: z-image pixel space (model still training atm) by @lodestone-rock in https://github.com/Comfy-Org/ComfyUI/pull/12709
• Fix VAEDecodeAudioTiled ignoring tile_size input (#12735) by @xeinherjer-dev in https://github.com/Comfy-Org/ComfyUI/pull/12738
• ModelPatcherDynamic: Force load all non-comfy weights by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12739
• main: Load aimdo after logger is setup by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12743
• Adjust memory usage factor of zeta model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12746
• CURVE type by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/12581
• DynamicVram: Add casting / fix torch Buffer weights by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12749
• Fix VideoFromComponents.save_to crash when writing to BytesIO by @artokun in https://github.com/Comfy-Org/ComfyUI/pull/12683
• model_patcher: Improve dynamic offload heuristic by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12759
• Comfy Aimdo 0.2.5 + Fix offload performance in DynamicVram by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12754
• Pass tokens when loading text gen model for text generation by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12755
• comfy-aimdo 0.2.6 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12764
• Initial load device should be cpu when using dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12766
• Support the LTXAV 2.3 model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12773
• Fix cublas ops on dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12776
• Update workflow templates to v0.9.6 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/12778
• Fix cuda getting initialized in cpu mode. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12779
• Update workflow templates to v0.9.7 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/12780

New Contributors

• @fappaz made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12665
• @vickytsang made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12641
• @ReinerBforartists made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12682
• @Talmaj made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12597
• @xeinherjer-dev made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12738

Full Changelog: https://github.com/Comfy-Org/ComfyUI/compare/v0.15.1...v0.16.0