What's Changed

• feat(V3-io): allow Enum classes for Combo options by @bigcat88 in #10237
• Refactor model sampling sigmas code. by @comfyanonymous in #10250
• Mvly/node update by @Kosinkadink in #10042
• feat(api-nodes, pylint): use lazy formatting in logging functions by @bigcat88 in #10248
• [V3] convert nodes_model_downscale.py to V3 schema by @bigcat88 in #10199
• [V3] convert nodes_lora_extract.py to V3 schema by @bigcat88 in #10182
• [V3] convert nodes_compositing.py to V3 schema by @bigcat88 in #10174
• [V3] convert nodes_latent.py to V3 schema by @bigcat88 in #10160
• More surgical fix for #10267 by @comfyanonymous in #10276
• fix(v3,api-nodes): V3 schema typing; corrected Pika API nodes by @bigcat88 in #10265
• [V3] convert nodes_sd3.py and nodes_slg.py to V3 schema by @bigcat88 in #10162
• Fix bug with applying loras on fp8 scaled without fp8 ops. by @comfyanonymous in #10279
• [V3] convert nodes_flux to V3 schema by @bigcat88 in #10122
• [V3] convert nodes_upscale_model.py to V3 schema by @bigcat88 in #10149
• Fix save audio nodes saving mono audio as stereo. by @comfyanonymous in #10289
• feat(GeminiImage-ApiNode): add aspect_ratio and release version of model by @bigcat88 in #10255
• feat(api-nodes): add price extractor feature; small fixes to Kling/Pika by @bigcat88 in #10284
• Update template to 0.1.95 by @comfyui-wiki in #10294
• Implement the mmaudio 16k VAE. by @comfyanonymous in #10300
• Improve AMD performance. by @comfyanonymous in #10302
• Update node docs to 0.3.0 by @comfyui-wiki in #10318
• update extra models paths example "clip" -> "text_encoders" by @christian-byrne in #10316
• Update the extra_model_paths.yaml.example by @comfyanonymous in #10319
• Always set diffusion model to eval() mode. by @comfyanonymous in #10331
• add indent=4 kwarg to json.dumps() in "Preview Any" node by @norgeous in #10307
• WAN2.2: Fix cache VRAM leak on error by @rattus128 in #10308
• [V3] convert nodes_hunyuan.py to V3 schema by @bigcat88 in #10136
• Enable RDNA4 pytorch attention on ROCm 7.0 and up. by @comfyanonymous in #10332
• Fix loading old stable diffusion ckpt files on newer numpy. by @comfyanonymous in #10333
• Better memory estimation for the SD/Flux VAE on AMD. by @comfyanonymous in #10334

New Contributors

• @norgeous made their first contribution in #10307

Full Changelog: v0.3.64...v0.3.65

What's Changed

• fix(api-nodes): enable more pylint rules by @bigcat88 in #10213
• fix(api-nodes): allow negative_prompt in PixVerse API nodes to be multiline by @bigcat88 in #10196
• [V3] convert nodes_pika.py to V3 schema by @bigcat88 in #10216
• [V3] convert nodes_kling.py to V3 schema by @bigcat88 in #10236
• Implement gemma 3 as a text encoder. by @comfyanonymous in #10241
• fix(ReCraft-API-node): allow custom multipart parser to return FormData by @bigcat88 in #10244
• feat(api-nodes): add Sora2 API node by @bigcat88 in #10249
• Temp fix for LTXV custom nodes. by @comfyanonymous in #10251
• Bump frontend to 1.27.10 by @webfiltered in #10252
• update template to 0.1.94 by @comfyui-wiki in #10253

Full Changelog: v0.3.63...v0.3.64

What's Changed

• Bump frontend to 1.27.7 by @AustinMroz in #10133
• [V3] convert nodes_audio_encoder.py to V3 schema by @bigcat88 in #10123
• [V3] convert nodes_gits.py to V3 schema by @bigcat88 in #9949
• [V3] convert nodes_differential_diffusion.py to V3 schema by @bigcat88 in #10056
• [V3] convert nodes_optimalsteps.py to V3 schema by @bigcat88 in #10074
• [V3] convert nodes_pag.py to V3 schema by @bigcat88 in #10080
• [V3] convert nodes_lt.py to V3 schema by @bigcat88 in #10084
• [V3] convert nodes_ip2p.pt to V3 schema by @bigcat88 in #10097
• Support the new hunyuan vae. by @comfyanonymous in #10150
• feat: Add Epsilon Scaling node for exposure bias correction by @Koratahiu in #10132
• sd: fix VAE tiled fallback VRAM leak by @rattus128 in #10139
• WAN VAE: Fix cache VRAM leak on error by @rattus128 in #10141
• Add a .bat to the AMD portable to disable smart memory. by @comfyanonymous in #10153
• [V3] convert nodes_morphology.py to V3 schema by @bigcat88 in #10159
• fix(api-nodes): made logging path to be smaller by @bigcat88 in #10156
• Turn on TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL by default. by @comfyanonymous in #10168
• [V3] update example_node.py to use V3 schema by @bigcat88 in #9723
• feat(linter, api-nodes): add pylint for comfy_api_nodes folder by @bigcat88 in #10157
• feat(api-nodes): add kling-2-5-turbo to txt2video and img2video nodes by @bigcat88 in #10155
• fix(api-nodes): reimport of base64 in Gemini node by @bigcat88 in #10181
• fix(api-nodes): bad indentation in Recraft API node function by @bigcat88 in #10175
• [V3] convert nodes_torch_compile.py to V3 schema by @bigcat88 in #10173
• [V3] convert nodes_eps.py to V3 schema by @bigcat88 in #10172
• [V3] convert nodes_pixverse.py to V3 schema by @bigcat88 in #10177
• [V3] convert nodes_tomesd.py to V3 schema by @bigcat88 in #10180
• [V3] convert nodes_edit_model.py to V3 schema by @bigcat88 in #10147
• Fix type annotation syntax in MotionEncoder_tc init by @Finn-Hecker in #10186
• Update amd nightly command in readme. by @comfyanonymous in #10189
• Add instructions to install nightly AMD pytorch for windows. by @comfyanonymous in #10190
• fix(api-nodes): enable 2 more pylint rules, removed non needed code by @bigcat88 in #10192
• [V3] convert nodes_rodin.py to V3 schema by @bigcat88 in #10195
• [V3] convert nodes_stable3d.py to V3 schema by @bigcat88 in #10204
• Remove soundfile dependency. No more torchaudio load or save. by @comfyanonymous in #10210
• fix(api-nodes): disable "std" mode for Kling2.5-turbo by @bigcat88 in #10212
• Remove useless code. by @comfyanonymous in #10223
• Update template to 0.1.93 by @comfyui-wiki in #10235

New Contributors

• @Koratahiu made their first contribution in #10132
• @Finn-Hecker made their first contribution in #10186

Full Changelog: v0.3.62...v0.3.63

What's Changed

• Workflow permission fix. by @comfyanonymous in #10110
• Add new portable links to readme. by @comfyanonymous in #10112
• fix(Rodin3D-Gen2): missing "task_uuid" parameter by @bigcat88 in #10128
• feat(api-nodes): enable Seedance Pro model in the FirstLastFrame node by @bigcat88 in #10120

Full Changelog: v0.3.61...v0.3.62

What's Changed

• Rodin3D - add [Rodin3D Gen-2 generate] api-node by @WhiteGiven in #9994
• Add new audio nodes by @kijai in #9908
• Fix issue with .view() in HuMo. by @comfyanonymous in #10014
• Fix memory leak by explicitly detaching model finalizer. by @guyniv in #9979
• Make LatentCompositeMasked work with basic video latents. by @comfyanonymous in #10023
• Try to fix the failing unit test. by @comfyanonymous in #10037
• Add @Kosinkadink as code owner by @yoland68 in #10041
• [V3] convert nodes_rebatch.py to V3 schema by @bigcat88 in #9945
• [V3] convert nodes_fresca.py to V3 schema by @bigcat88 in #9951
• [V3] convert nodes_sdupscale.py to V3 schema by @bigcat88 in #9943
• [V3] convert nodes_tcfg.py to V3 schema by @bigcat88 in #9942
• [V3] convert nodes_sag.py to V3 schema by @bigcat88 in #9940
• [V3] convert nodes_post_processing to V3 schema by @bigcat88 in #9491
• [V3] convert CLIPTextEncodeSDXL nodes to V3 schema by @bigcat88 in #9716
• Don't add template to qwen2.5vl when template is in prompt. by @comfyanonymous in #10043
• Add 'input_cond' and 'input_uncond' to sampler_cfg_function args dictionary by @Kosinkadink in #10044
• Update template to 0.1.88 by @comfyui-wiki in #10046
• Add workflow templates version tracking to system_stats response by @christian-byrne in #9089
• [V3] convert nodes_hidream.py to V3 schema by @bigcat88 in #9946
• [V3] convert nodes_bfl.py to V3 schema by @bigcat88 in #10033
• [V3] convert nodes_luma.py to V3 schema by @bigcat88 in #10030
• [V3] convert nodes_pixart.py to V3 schema by @bigcat88 in #10019
• [V3] convert nodes_photomaker.py to V3 schema by @bigcat88 in #10017
• [V3] convert nodes_qwen.py to V3 schema by @bigcat88 in #10049
• Reduce Peak WAN inference VRAM usage - part II by @rattus128 in #10062
• Improvements to the stable release workflow. by @comfyanonymous in #10065
• Fix typo in release workflow. by @comfyanonymous in #10066
• [V3] convert nodes_lotus.py to V3 schema by @bigcat88 in #10057
• [V3] convert nodes_lumina2.py to V3 schema by @bigcat88 in #10058
• [V3] convert nodes_hypertile.py to V3 schema by @bigcat88 in #10061
• feat: ComfyUI can be run on the specified Ascend NPU by @muxuezzz in #9663
• Fix stable workflow creating multiple draft releases. by @comfyanonymous in #10067
• Update command to install latest nighly pytorch. by @comfyanonymous in #10085
• [Rodin3d api nodes] Updated the name of the save file path (changed from timestamp to UUID). by @WhiteGiven in #10011
• Update template to 0.1.91 by @comfyui-wiki in #10096
• feat(api-nodes): add WanImageToImageApi node by @bigcat88 in #10094
• [V3] convert nodes_mochi.py to V3 schema by @bigcat88 in #10069
• [V3] convert nodes_perpneg.py to V3 schema by @bigcat88 in #10081
• Don't cache new locale-based templates entry point files by @christian-byrne in #10101
• [V3] convert nodes_mahiro.py to V3 schema by @bigcat88 in #10070
• Add action to create cached deps with manually specified torch. by @comfyanonymous in #10102
• Make the final release test optional in the stable release action. by @comfyanonymous in #10103
• Different base files for different release. by @comfyanonymous in #10104
• Different base files for nvidia and amd portables. by @comfyanonymous in #10105
• Add a way to have different names for stable nvidia portables. by @comfyanonymous in #10106
• Add action to do the full stable release. by @comfyanonymous in #10107
• Make stable release workflow callable. by @comfyanonymous in #10108
• Add basic readme for AMD portable. by @comfyanonymous in #10109

New Contributors

• @WhiteGiven made their first contribution in #9994
• @guyniv made their first contribution in #9979
• @muxuezzz made their first contribution in #9663

Full Changelog: v0.3.60...v0.3.61

What's Changed

• Support hunyuan image distilled model. by @comfyanonymous in #9807
• Update template to 0.1.81 by @comfyui-wiki in #9811
• Fast preview for hunyuan image. by @comfyanonymous in #9814
• Implement hunyuan image refiner model. by @comfyanonymous in #9817
• Add Output to V3 Combo type to match what is possible with V1 by @Kosinkadink in #9813
• Bump frontend to 1.26.11 by @benceruleanlu in #9809
• Add noise augmentation to hunyuan image refiner. by @comfyanonymous in #9831
• Fix hunyuan refiner blownout colors at noise aug less than 0.25 by @comfyanonymous in #9832
• Set default hunyuan refiner shift to 4.0 by @comfyanonymous in #9833
• API nodes: add kling-v2-1 model to the KlingStartEndFrame node by @bigcat88 in #9630
• [V3] convert Minimax API nodes to the V3 schema by @bigcat88 in #9693
• [V3] convert WanCameraEmbedding node to V3 schema by @bigcat88 in #9714
• [V3] convert Cosmos nodes to V3 schema by @bigcat88 in #9721
• [V3] convert nodes_cond.py to V3 schema by @bigcat88 in #9719
• [V3] convert CFG nodes to V3 schema by @bigcat88 in #9717
• [V3] convert Canny node to V3 schema by @bigcat88 in #9743
• [V3] convert Moonvalley API nodes to the V3 schema by @bigcat88 in #9698
• Better way of doing the generator for the hunyuan image noise aug. by @comfyanonymous in #9834
• Enable Runtime Selection of Attention Functions by @Kosinkadink in #9639
• Hunyuan refiner vae now works with tiled. by @comfyanonymous in #9836
• Support wav2vec base models by @kijai in #9637
• Cleanup. by @comfyanonymous in #9838
• HunyuanImage: Remove single quote pattern to avoid wrong text matches by @KimbingNg in #9842
• Add support for Chroma Radiance by @blepping in #9682
• Changes to the previous radiance commit. by @comfyanonymous in #9851
• Make ModuleNotFoundError ImportError instead by @Kosinkadink in #9850
• Add that hunyuan image is supported to readme. by @comfyanonymous in #9857
• Support the omnigen2 umo lora. by @comfyanonymous in #9886
• Fix python -O and BatchedBrownianTree w0 handling by @blepping in #9884
• Add encoder part of whisper large v3 as an audio encoder model. by @comfyanonymous in #9894
• Reduce Peak WAN inference VRAM usage by @rattus128 in #9898
• Support the 1.7B HuMo model. by @comfyanonymous in #9903
• Support the HuMo 17B model. by @comfyanonymous in #9912
• Enable fp8 ops by default on gfx1200 by @0xDELUXA in #9926
• Fix image sharpen node by @jetjodh in #9932
• Do padding of audio embed in model for humo for more flexibility. by @comfyanonymous in #9935
• Bump frontend to 1.26.13 by @christian-byrne in #9933
• Basic WIP support for the wan animate model. by @comfyanonymous in #9939
• fix(api_nodes): reduce default timeout from 7 days to 2 hours by @bigcat88 in #9918
• fix(seedream4): add flag to ignore error on partial success by @bigcat88 in #9952
• Update WanAnimateToVideo to more easily extend videos. by @comfyanonymous in #9959
• Add inputs for character replacement to the WanAnimateToVideo node. by @comfyanonymous in #9960
• [Reviving #5709] Add strength input to Differential Diffusion by @Kosinkadink in #9957
• Fix LoRA Trainer bugs with FP8 models. by @KohakuBlueleaf in #9854
• Lower wan memory estimation value a bit. by @comfyanonymous in #9964
• Set some wan nodes as no longer experimental. by @comfyanonymous in #9976
• Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus node. by @comfyanonymous in #9986
• Add offset param to /history endpoint by @christian-byrne in #9977
• Fix bug with WanAnimateToVideo node. by @comfyanonymous in #9988
• Fix bug with WanAnimateToVideo. by @comfyanonymous in #9990
• update template to 0.1.86 by @comfyui-wiki in #9998
• feat(api-nodes): add wan t2i, t2v, i2v nodes by @bigcat88 in #9996

New Contributors

• @KimbingNg made their first contribution in #9842
• @rattus128 made their first contribution in #9898
• @0xDELUXA made their first contribution in #9926
• @jetjodh made their first contribution in #9932

Full Changelog: v0.3.59...v0.3.60

What's Changed

• add new ByteDanceSeedream (4.0) node by @bigcat88 in #9802
• Update template to 0.1.78 by @comfyui-wiki in #9806

Full Changelog: v0.3.58...v0.3.59

What's Changed

• Fix progress update crossover between users by @guill in #9706
• Add Hunyuan 3D 2.1 Support by @yousef-rafat in #8714
• Some changes to the previous hunyuan PR. by @comfyanonymous in #9725
• fix: add cache headers for images by @arjansingh in #9560
• Fix lowvram issues with hunyuan3d 2.1 by @comfyanonymous in #9735
• Print all fast options in --help by @comfyanonymous in #9737
• Enable bf16 VAE on RDNA4. by @comfyanonymous in #9746
• Don't enable pytorch attention on AMD if triton isn't available. by @comfyanonymous in #9747
• Fix amd_min_version crash when cpu device. by @comfyanonymous in #9754
• Add ZeroDivisionError catch for EasyCache logging statement by @Kosinkadink in #9768
• Add explicit casting in apply_rope for Qwen VL by @contentis in #9759
• Support qwen inpaint controlnet. by @comfyanonymous in #9772
• API nodes: add ByteDance video by @bigcat88 in #9712
• Small refactor of some vae code. by @comfyanonymous in #9787
• Change validate_inputs' output typehint to 'bool | str' and update docstrings by @Kosinkadink in #9786
• Fix issue on old torch. by @comfyanonymous in #9791
• Support hunyuan image 2.1 regular model. by @comfyanonymous in #9792
• Update template to 0.1.76 by @comfyui-wiki in #9793
• Fix lowvram issue with hunyuan image vae. by @comfyanonymous in #9794
• API nodes: add StabilityAI Audio API nodes by @bigcat88 in #9749

New Contributors

• @yousef-rafat made their first contribution in #8714
• @arjansingh made their first contribution in #9560

Full Changelog: v0.3.57...v0.3.58

What's Changed

• convert Stable Cascade nodes to V3 schema by @bigcat88 in #9373
• [V3] convert Video nodes to V3 schema by @bigcat88 in #9489
• [V3] convert nodes_stability.py to V3 schema by @bigcat88 in #9497
• convert Primitive nodes to V3 schema by @bigcat88 in #9372
• SEEDS: update noise decomposition and refactor by @chaObserv in #9633
• Probably not necessary anymore. by @comfyanonymous in #9646
• Implement the USO subject identity lora. by @comfyanonymous in #9674
• Enable Convolution AutoTuning by @contentis in #9301
• USO style reference. by @comfyanonymous in #9677
• uso -> uxo/uno as requested. by @comfyanonymous in #9688
• Accept prompt_id in interrupt handler by @deepanjanroy in #9607
• ImageScaleToMaxDimension node. by @comfyanonymous in #9689
• Update template to 0.1.73 by @comfyui-wiki in #9686
• feat(api-nodes): add ByteDance Image nodes by @bigcat88 in #9477
• api nodes(Ideogram): add Ideogram Character by @bigcat88 in #9616
• [V3] convert Runway API nodes to the V3 schema by @bigcat88 in #9487
• Update comment in api example. by @comfyanonymous in #9708
• convert AlignYourStepsScheduler node to V3 schema by @bigcat88 in #9226
• Fix potential rope issue. by @comfyanonymous in #9710
• Update template to 0.1.75 by @comfyui-wiki in #9711

New Contributors

• @deepanjanroy made their first contribution in #9607

Full Changelog: v0.3.56...v0.3.57

What's Changed

• Lower ram usage on windows. by @comfyanonymous in #9628

Full Changelog: v0.3.55...v0.3.56