## What's Changed * Add manual cast to LTX2 vocoder conv_transpose1d by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12795 * LTX audio vae novram fixes. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12796 * feat: add causal_fix parameter to add_keyframe_index and append_keyframe by @tavihalperin in https://github.com/Comfy-Org/ComfyUI/pull/12797 **Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.16.2...v0.16.3

## What's Changed * Support the 4B ace step 1.5 lm model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12257 * Dynamic_vram: Remove Aimdo exemption for empty_cache (fixes VRAM leak) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12260 * Fix crash with ace step 1.5 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12264 **Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.12.1...v0.12.2

## What's Changed * Revert "Force sequential execution in CI test jobs" by @yoland68 in https://github.com/Comfy-Org/ComfyUI/pull/11725 * bump comfyui_manager version to the 4.0.5 by @ltdrdata in https://github.com/Comfy-Org/ComfyUI/pull/11732 * Better detection if AMD torch compiled with efficient attention. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11745 * Fix import issue. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11746 * Add node: JoinAudioChannels by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/11728 * Fix csp error in frontend when forcing offline. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11749 * Bump comfyui-frontend-package to 1.36.13 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/11645 * Add most basic Asset support for models by @Kosinkadink in https://github.com/Comfy-Org/ComfyUI/pull/11315 * Fix VAEEncodeForInpaint to support WAN VAE tuple downscale_ratio by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/11572 * add node - image compare by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/11343 * feat: add 'cancelled' status for interrupted jobs in /api/jobs by @ric-yu in https://github.com/Comfy-Org/ComfyUI/pull/11680 * Add workaround for a hacky nodepack existing by @Kosinkadink in https://github.com/Comfy-Org/ComfyUI/pull/11755 * Be less strict when loading mixed ops weights. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11769 * fix(api-nodes): do not downscale the input image for Topaz Enhance by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11768 * [API Nodes] add nodes for Vidu2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11760 * Update embedded docs to v0.4.0 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/11776 * Properly save mixed ops. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11772 * Enable PyTorch Attention by default on gfx1200 by @0xDELUXA in https://github.com/Comfy-Org/ComfyUI/pull/11793 * Fix issue with t5 text encoder in fp4. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11794 * Fix chroma fp8 te being treated as fp16. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11795 * fix(api-nodes): use a unique name for uploading audio files by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11778 * Put more details about portable in readme. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11816 * Support ModelScope-Trainer/DiffSynth LoRA format for Z-Image models by @kelseyee in https://github.com/Comfy-Org/ComfyUI/pull/11805 * Support the siglip 2 naflex model as a clip vision model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11831 * Reduce LTX2 VRAM use by more efficient timestep embed handling by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/11829 * Update workflow templates to v0.8.0 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/11828 * Update workflow templates to v0.8.4 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/11835 * Make loras work on nvfp4 models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11837 * Refactor to try to lower mem usage. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11840 * Make database bulk_ops.py more widely compatible across sqlalchemy+python versions by @Kosinkadink in https://github.com/Comfy-Org/ComfyUI/pull/11839 * Patch frontend to 1.36.14 (from 1.36.13) by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/11841 ## New Contributors * @kelseyee made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/11805 **Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.8.2...v0.9.0

## What's Changed * Add support for sage attention 3 in comfyui, enable via new cli arg by @mengqin in https://github.com/Comfy-Org/ComfyUI/pull/11026 * V3 Improvements + DynamicCombo + Autogrow exposed in public API by @Kosinkadink in https://github.com/Comfy-Org/ComfyUI/pull/11345 * fix(api-nodes-vidu): preserve percent-encoding for signed URLs by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11564 * Update workflow templates to v0.7.65 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/11579 * Refactor: move clip_preprocess to comfy.clip_model by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11586 * Remove duplicate import of model_management by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11587 * New Year ruff cleanup. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11595 * Ignore all frames except the first one for MPO format. by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11569 * Give Mahiro CFG a more appropriate display name by @throttlekitty in https://github.com/Comfy-Org/ComfyUI/pull/11580 * [API Nodes] Tripo3D: pass face_limit parameter only when it differs from default by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11601 * Remove leftover scaled_fp8 key. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11603 * Print memory summary on OOM to help with debugging. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11613 * [API Nodes] add support for 720p resolution for Kling Omni nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11604 * Fix case where upscale model wouldn't be moved to cpu. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11633 * Support the LTXV 2 model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11632 * Add LTXAVTextEncoderLoader node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11634 * Refactor module_size function. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11637 * Fix name. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11638 * Initial ops changes to use comfy_kitchen: Initial nvfp4 checkpoint support. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11635 * Use rope functions from comfy kitchen. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11647 * Revert "Use rope functions from comfy kitchen." by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11648 * Update workflow templates to v0.7.66 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/11652 * Add helpful message to portable. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11671 * Update comfy-kitchen version to 0.2.1 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11672 * Use rope functions from comfy kitchen. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11674 * Update workflow templates to v0.7.67 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/11667 * Fix lowvram issue with ltxv2 text encoder. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11675 * Disable ltxav previews. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11676 * Skip fp4 matrix mult on devices that don't support it. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11677 * Disable comfy kitchen cuda if pytorch cuda less than 13 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11681 * Update comfy-kitchen version to 0.2.3 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11685 * Force sequential execution in CI test jobs by @yoland68 in https://github.com/Comfy-Org/ComfyUI/pull/11687 * [API Nodes] add WAN2.6 ReferenceToVideo by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/11644 * Fix fp8 fast issue. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11688 ## New Contributors * @mengqin made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/11026 * @throttlekitty made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/11580 **Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.7.0...v0.8.0

## What's Changed * Bump comfyui-frontend-package to 1.35.9 by @comfy-pr-bot in https://github.com/comfyanonymous/ComfyUI/pull/11470 * Update workflow templates to v0.7.64 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/11496 * Add a ManualSigmas node. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11499 * Specify in readme that we only support pytorch 2.4 and up. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11512 * bump comfyui_manager version to the 4.0.4 by @ltdrdata in https://github.com/comfyanonymous/ComfyUI/pull/11521 * Fix noise with ancestral samplers when inferencing on cpu. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11528 * feat(api-nodes): add Kling Motion Control node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11493 * [V3] converted nodes_images.py to V3 schema by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11206 * fix(api-nodes-gemini): always force enhance_prompt to be True by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11503 * chore(api-nodes): move to credits from $ by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11489 * Enable async offload by default for AMD. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11534 * Comment out unused norm_final in lumina/z image model. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11545 * mm: discard async errors from pinning failures by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10738 * Add some warnings for pin and unpin errors. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11561 * ResizeByLongerSide: support video by @tavihalperin in https://github.com/comfyanonymous/ComfyUI/pull/11555 * Mark "seededit" as deprecated, adjust display name of Seedream node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11490 * Add handling for vace_context in context windows by @drozbay in https://github.com/comfyanonymous/ComfyUI/pull/11386 ## New Contributors * @tavihalperin made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/11555 **Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.6.0...v0.7.0

## What's Changed * Resolution bucketing and Trainer implementation refactoring by @KohakuBlueleaf in https://github.com/comfyanonymous/ComfyUI/pull/11117 * skip_load_model -> force_full_load by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11390 * Add unified jobs API with /api/jobs endpoints by @ric-yu in https://github.com/comfyanonymous/ComfyUI/pull/11054 * Update workflow templates to v0.7.60 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/11403 * Support loading Wan/Qwen VAEs with different in/out channels. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11405 * Trim/pad channels in VAE code. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11406 * Diffusion model part of Qwen Image Layered. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11408 * Add LatentCutToBatch node. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11411 * [API Nodes] add Flux2MaxImage API Node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11420 * bump comfyui_manager version to the 4.0.3b7 by @ltdrdata in https://github.com/comfyanonymous/ComfyUI/pull/11422 * Allow enabling use of MIOpen by setting an env var by @BradPepersAMD in https://github.com/comfyanonymous/ComfyUI/pull/11366 * Support nested tensor denoise masks. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11431 * Fix error from logging line in Context Windows by @drozbay in https://github.com/comfyanonymous/ComfyUI/pull/11423 * Implement sliding attention in Gemma3 by @woct0rdho in https://github.com/comfyanonymous/ComfyUI/pull/11409 * Disable prompt weights on newbie te. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11434 * ZImageFunControlNet: Fix mask concatenation in --gpu-only by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/11421 * Fix issue with batches and newbie. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11435 * Implement Jina CLIP v2 and NewBie dual CLIP by @woct0rdho in https://github.com/comfyanonymous/ComfyUI/pull/11415 * Only apply gemma quant config to gemma model for newbie. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11436 * chore(api-nodes): by default set Watermark generation to False by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11437 * fix(api-nodes): Topaz 4k video upscaling by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11438 * Core release process. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11447 * Add node to create empty latents for qwen image layered model. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11460 * [API Nodes] extend possible duration range for Kling O1 StartEndFrame node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11451 * Update workflow templates to v0.7.62 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/11467 * Make denoised output on custom sampler nodes work with nested tensors. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11471 * api-nodes: use new custom endpoint for Nano Banana by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11311 * Update workflow templates to v0.7.63 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/11482 ## New Contributors * @BradPepersAMD made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/11366 * @woct0rdho made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/11409 **Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.5.1...v0.6.0

## What's Changed * [API Nodes] GPT-Image-1.5 by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11368 * fix regression in V3 nodes processing by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11375 * SA-Solver: return the result of the last predictor step correctly by @chaObserv in https://github.com/comfyanonymous/ComfyUI/pull/11380 * Better handle torch being imported by prestartup nodes. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11383 **Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.5.0...v0.5.1

## What's Changed * Bump frontend to 1.34.8 by @benceruleanlu in https://github.com/comfyanonymous/ComfyUI/pull/11220 * fix: correctly process the Node V1 dict results on V3 node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11237 * Tweak Z Image memory estimation. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11254 * Fix: filter hidden files from /internal/files endpoint by @Myestery in https://github.com/comfyanonymous/ComfyUI/pull/11191 * Lower VAE loading requirements：Create a new branch for GPU memory calculations in qwen-image vae by @jiangchengchengark in https://github.com/comfyanonymous/ComfyUI/pull/11199 * feat(api-nodes): enable Kling Omni Image node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11229 * Adjust memory usage factor for sd3. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11257 * Fix regular chroma radiance by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11276 * This only works on radiance. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11277 * Better chroma radiance vram estimation. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11278 * Make portable updater work with repos in unmerged state. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11281 * WanMove support by @kijai in https://github.com/comfyanonymous/ComfyUI/pull/11247 * Respect the dtype the op was initialized in for non quant mixed op. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11282 * feat(api-nodes): Kling TextToVideoWithAudio and ImageToVideoWithAudio nodes by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11267 * Fix bias dtype issue in mixed ops. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11293 * Basic implementation of z image fun control union 2.0 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11304 * Fix pytorch warnings. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11314 * seeds_2: add phi_2 variant and sampler node by @chaObserv in https://github.com/comfyanonymous/ComfyUI/pull/11309 * Update warning for old pytorch version. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11319 * bump manager to the 4.0.3b5 by @ltdrdata in https://github.com/comfyanonymous/ComfyUI/pull/11324 * Update workflow templates to v0.7.59 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/11337 * Disable guards on transformer_options when torch.compile by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11317 * [API Nodes] drop very old Kling models by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11307 * drop Pika API nodes by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11306 * feat(preview): add per-queue live preview method override by @ltdrdata in https://github.com/comfyanonymous/ComfyUI/pull/11261 * comfy_api: remove usage of "Type","List" and "Dict" types by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11238 * Add context windows callback for custom cond handling by @drozbay in https://github.com/comfyanonymous/ComfyUI/pull/11208 * Support the new qwen edit 2511 reference method. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11340 * [add] tripo3.0 by @seed93 in https://github.com/comfyanonymous/ComfyUI/pull/10663 * Add code to detect if a z image fun controlnet is broken or not. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11341 * [BlockInfo] Lumina by @Haoming02 in https://github.com/comfyanonymous/ComfyUI/pull/11227 * [BlockInfo] Wan by @Haoming02 in https://github.com/comfyanonymous/ComfyUI/pull/10845 * Only enable fp16 on ZImage on newer pytorch. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11344 * Patch frontend to 1.34.9 (from 1.34.8) by @christian-byrne in https://github.com/comfyanonymous/ComfyUI/pull/11342 * Inpainting for z image fun control. Use the ZImageFunControlnet node. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11346 * Add a way to set the default ref method in the qwen image code. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11349 * Update workflows for new release process by @benceruleanlu in https://github.com/comfyanonymous/ComfyUI/pull/11064 * [API Nodes] add Wan2.6 model to video nodes by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11357 * Check state dict key to auto enable the index_timestep_zero ref method. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11362 * Add exp_heun_2_x0 sampler series by @chaObserv in https://github.com/comfyanonymous/ComfyUI/pull/11360 ## New Contributors * @jiangchengchengark made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/11199 * @drozbay made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/11208 * @seed93 made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/10663 **Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.4.0...v0.5.0