• Fix for Gemini/Nano banana api nodes that sometimes returned a blank image.
  Full Changelog:v0.14.1...v0.14.2

What's Changed

• Fix anima LLM adapter forward when manual cast by@chaObserv in#12504
• feat(api-nodes): add "viduq3-turbo" model support by@bigcat88 in#12482
• feat(api-nodes): add Recraft V4 nodes by@bigcat88 in#12502
• Update workflow templates to v0.8.43 by@comfyui-wiki in#12507

Full Changelog:v0.14.0...v0.14.1

Contributors

What's Changed

• mp: dont deep-clone objects from model_options by@rattus128 in#12382
• sd: delay VAE dtype archive until after override by@rattus128 in#12388
• dynamic_vram: ops: Fix vanilla-fp8 loaded lora quality by@rattus128 in#12390
• Fix 3D models not showing in outputs window by@guill in#12381
• Add a VideoSlice node by@AustinMroz in#12107
• [Trainer] training with proper offloading by@KohakuBlueleaf in#12189
• Make built in lora training work on anima. by@comfyanonymous in#12402
• fix(api-nodes): retry on connection errors during polling instead of aborting by@bigcat88 in#12393
• Dispatch desktop auto-bump when a ComfyUI release is published by@benceruleanlu in#12398
• [API Nodes] enable Magnific Upscalers by@bigcat88 in#12179
• dynamic_vram: Fix windows Aimdo crash + Fix LLM performance by@rattus128 in#12408
• ace15: Use dynamic_vram friendly trange by@rattus128 in#12409
• model_patcher: guard against none model_dtype by@rattus128 in#12410
• Update ace15.py to allow min_p sampling by@askmyteapot in#12373
• Add a tip for common error. by@comfyanonymous in#12414
• fix(api-nodes): add separate retry budget for 429 rate limit responses by@bigcat88 in#12421
• ModelPatcherDynamic: force load non leaf weights by@rattus128 in#12433
• llama: use a more efficient rope implementation by@rattus128 in#12434
• Update command to install AMD stable linux pytorch. by@comfyanonymous in#12437
• dynamic_vram: Training fixes by@rattus128 in#12442
• Use torch RMSNorm for flux models and refactor hunyuan video code. by@comfyanonymous in#12432
• Support generating attention masks for left padded text encoders. by@comfyanonymous in#12454
• Fix some custom nodes. by@comfyanonymous in#12455
• Add left padding to LTXAV text encoder. by@comfyanonymous in#12456
• Add working Qwen 2512 ControlNet (Fun ControlNet) support by@krigeta in#12359
• Patch frontend to 1.38.14 (from 1.38.13) by@christian-byrne in#12469
• Remove unsafe pickle loading code that was used on pytorch older than 2.4 by@comfyanonymous in#12473
• chore(api-nodes): remove "gpt-4o" model by@bigcat88 in#12467
• Node Replacement API by@Kosinkadink in#12014
• feat(api-nodes-Tencent): add ModelTo3DUV, 3DTextureEdit, 3DParts nodes by@bigcat88 in#12428
• feat(api-nodes): add Bria RMBG nodes by@bigcat88 in#12465
• Fix lora Extraction in offload conditions (+ dynamic_vram mode) by@rattus128 in#12479
• MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) by@rattus128 in#12446
• Remove workaround for old pytorch. by@comfyanonymous in#12480
• Update workflow templates to v0.8.42 by@comfyui-wiki in#12491
• Remove code to support RMSNorm on old pytorch. by@comfyanonymous in#12499
• gitignore venv* by@alexheretic in#12431
• Allow control_after_generate to be type ControlAfterGenerate in v3 schema by@Kosinkadink in#12187
• Implement NAG on all the models based on the Flux code. by@comfyanonymous in#12500
• Fix anima preprocess text embeds not using right inference dtype. by@comfyanonymous in#12501

New Contributors

• @askmyteapot made their first contribution in#12373
• @krigeta made their first contribution in#12359

Full Changelog:v0.13.0...v0.14.0

Contributors

What's Changed

• Bump comfyui-frontend-package to 1.38.13 by@comfy-pr-bot in#12238
• Add a Create List node by@AustinMroz in#12173
• Make ace step 1.5 work without the llm. by@comfyanonymous in#12311
• Fix some lowvram stuff with ace step 1.5 by@comfyanonymous in#12312
• Fix issue when using disable_unet_model_creation by@comfyanonymous in#12315
• EasyCache: Support LTX2 by@kijai in#12231
• Make ace step 1.5 base model work properly with default workflow. by@comfyanonymous in#12337
• Fix return_word_ids=True with Anima tokenizer by@asagi4 in#12328
• Fix bug with last pr by@comfyanonymous in#12338
• Support fp16 for Cosmos-Predict2 and Anima by@tdrussell in#12249
• Some fixes to previous pr. by@comfyanonymous in#12339
• Pad ace step 1.5 ref audio is not long enough. by@comfyanonymous in#12341
• Fix LazyCache by@kijai in#12344
• Add search_aliases to sa-solver and seeds-2 node by@chaObserv in#12327
• Update embedded docs to v0.4.1 by@comfyui-wiki in#12346
• Disable prompt weights for ltxv2. by@comfyanonymous in#12354
• Make tonemap latent work on any dim latents. by@comfyanonymous in#12363
• Dynamic VRAM fixes - Ace 1.5 performance + a VRAM leak by@rattus128 in#12368
• Iimprovements to ACE-Steps 1.5 text encoding (part 2) by@blepping in#12350
• Ace step prompts match now. by@comfyanonymous in#12376
• Update workflow templates to v0.8.37 by@comfyui-wiki in#12377
• fix(Moonvalley-API-Nodes): adjust "steps" parameter to not raise exception by@bigcat88 in#12370
• feat(api-nodes-Kling): add new models (V3, O3) by@bigcat88 in#12389
• Update workflow templates to v0.8.38 by@comfyui-wiki in#12394

New Contributors

• @tdrussell made their first contribution in#12249

Full Changelog:v0.12.3...v0.13.0

Contributors

What's Changed

• Fix crash on safetensors load for some 3rd party Models by@rattus128 in#12266
• mp: Fix checkpoint saving by@rattus128 in#12268
• add File3DAny output to Load3D node; extend SaveGLB to accept File3DAny as input by@bigcat88 in#12276
• Fix ace step nan issue on some hardware/pytorch configs. by@comfyanonymous in#12289
• Try to fix ace text encoder slowness on some configs. by@comfyanonymous in#12290
• Add llm sampling options and make reference audio work on ace step 1.5 by@comfyanonymous in#12295
• Disable sage attention on ace step 1.5 by@comfyanonymous in#12297
• Improvements to ACE-Steps 1.5 text encoding by@blepping in#12283
• Add VAE tiled decode node for audio. by@comfyanonymous in#12299

Full Changelog:v0.12.2...v0.12.3

Contributors

What's Changed

• Support the 4B ace step 1.5 lm model. by@comfyanonymous in#12257
• Dynamic_vram: Remove Aimdo exemption for empty_cache (fixes VRAM leak) by@rattus128 in#12260
• Fix crash with ace step 1.5 by@comfyanonymous in#12264

Full Changelog:v0.12.1...v0.12.2

Contributors

What's Changed

• Add progress bar to ace step. by@comfyanonymous in#12242
• Fix some issues with mac. by@comfyanonymous in#12247
• llama: cast logits as a comfy-weight by@comfyanonymous in#12248
• Fix mac issue. by@comfyanonymous in#12250
• feat(comfy_api): add basic 3D Model file types by@bigcat88 in#12129
• Support ace step 1.5 base model loras. by@comfyanonymous in#12252
• Fix tiled vae for ace step 1.5 by@comfyanonymous in#12253

Full Changelog:v0.12.0...v0.12.1

Contributors

What's Changed

• fix: count non-dict items in outputs_count by@christian-byrne in#12166
• Make empty hunyuan latent 1.0 work with the 1.5 model. by@comfyanonymous in#12171
• Remove unused code from _io.py by@Kosinkadink in#12147
• [API Nodes] RecraftCreateStyleNode node by@bigcat88 in#12055
• Add color type and Color to RGB Int node by@pythongosssss in#12145
• Update python patch version in dep workflow. by@comfyanonymous in#12184
• Fix model not working with any res. by@comfyanonymous in#12186
• [API Nodes] Vidu: Q3 model; Extend and MultiFrame nodes by@bigcat88 in#12175
• Assets Part 2 - add more endpoints by@Kosinkadink in#12125
• Send is_input_list on v1 and v3 schema to frontend by@Kosinkadink in#12188
• KV cache implementation for using llama models for text generation. by@comfyanonymous in#12195
• Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading by@rattus128 in#11845
• fix: improve error message when node type is missing by@christian-byrne in#12194
• Fix some custom nodes breaking. by@comfyanonymous in#12203
• dynamic_vram: fix pinning with model defined dtype by@rattus128 in#12208
• dynamic_vram: respect argument cast dtypes in non-comfy weights by@rattus128 in#12209
• dynamic_vram: silence pytorch buffer warning by@rattus128 in#12210
• requirements: bump comfy-aimdo to 0.1.7 by@rattus128 in#12211
• Fix issue with parameters on root model object. by@comfyanonymous in#12216
• Enable embeddings for some qwen 3 models. by@comfyanonymous in#12218
• mm: Fix cast buffers with intel offloading by@rattus128 in#12229
• Dynamic VRAM unloading fix by@rattus128 in#12227
• Add back function. by@comfyanonymous in#12234
• [API Nodes] HitPaw API nodes by@bigcat88 in#12117
• Basic support for the ace step 1.5 model. by@comfyanonymous in#12237
• Update workflow templates to v0.8.31 by@comfyui-wiki in#12239

Full Changelog:v0.11.1...v0.12.0

Contributors

What's Changed

• Add support for dev-only nodes. by@guill in#12106
• Update Python 3.14 compatibility notes in README by@comfyanonymous in#12127
• [API Nodes] Grok Imagine nodes by@bigcat88 in#12136
• bump manager version to 4.1b1 by@ltdrdata in#12140
• Update workflow templates to v0.8.27 by@comfyui-wiki in#12141
• Add missing spacial downscale ratios. by@comfyanonymous in#12146

Full Changelog:v0.11.0...v0.11.1

Contributors

What's Changed

• Support zimage omni base model. by@comfyanonymous in#11979
• Update workflow templates to v0.8.15 by@comfyui-wiki in#11984
• Bump comfyui-frontend-package to 1.37.11 by@comfy-pr-bot in#11976
• Make omni stuff work on regular z image for easier testing. by@comfyanonymous in#11985
• [API Nodes] add WaveSpeed nodes by@bigcat88 in#11945
• fix: remove normalization of audio in LTX Mel spectrogram creation by@izorinLightricks in#11990
• Dynamically detect chroma radiance patch size by@gitmylo in#11991
• Config for Qwen 3 0.6B model. by@comfyanonymous in#11998
• Add LyCORIS LoKr support for Flux2 by@markuryy in#11997
• [API Nodes] allow passing up to 7 subjects in Vidu Reference node by@bigcat88 in#12002
• feat: Add search_aliases field to node schema by@christian-byrne in#12010
• Support the Anima model. by@comfyanonymous in#12012
• Fix for edge case of EasyCache when conditionings change during a sampling run by@Kosinkadink in#12020
• Support LTX2 Tiny VAE (taeltx_2) by@kijai in#11929
• LTX2: Further reduce warnings when loading embeddings_connector weights by@kijai in#11992
• Support Multi/InfiniteTalk by@kijai in#10179
• [API Nodes] rename BriaImage and OpenAIGImage nodes by@bigcat88 in#12022
• add ply & 3dgs format in 3d node by@jtydhr88 in#11474
• Reduce LTX2 VAE VRAM consumption by@rattus128 in#12028
• Support loading flux 2 klein checkpoints saved with SaveCheckpoint. by@comfyanonymous in#12033
• Propagate Qwen-Image attention mask to image generation. by@maromri in#11966
• add search aliases to all nodes by@christian-byrne in#12035
• feat: Improve ResizeImageMaskNode UX with tooltips, and search aliases by@christian-byrne in#12013
• Revert "feat: Improve ResizeImageMaskNode UX with tooltips, and search aliases" by@comfyanonymous in#12038
• feat: Improve ResizeImageMaskNode UX with tooltips and search aliases by@christian-byrne in#12040
• LTX2: Refactor forward function for better VRAM efficiency and fix spatial inpainting by@kijai in#12046
• Support ModelScope-Trainer/DiffSynth LoRA format for Flux.2 Klein models by@comfyui-wiki in#12042
• Make regular empty latent node work properly on flux 2 variants. by@comfyanonymous in#12050
• speed up and reduce VRAM of QWEN VAE and WAN (less so) by@rattus128 in#12036
• Make empty latent node work with other models. by@comfyanonymous in#12062
• [API Nodes] add TencentHunyuan3D nodes by@bigcat88 in#12026
• Add support for kwargs inputs to allow arbitrary inputs from frontend by@pythongosssss in#12063
• Only enable fp16 on z image models that actually support it. by@comfyanonymous in#12065
• [Weight-adapter/Trainer] Bypass forward mode in Weight adapter system by@KohakuBlueleaf in#11958
• Move nodes from previous PR into their own file. by@comfyanonymous in#12066
• Add name to LoraLoaderModelOnly. by@comfyanonymous in#12078
• Fix mistral 3 tokenizer code failing on latest transformers version and other breakage. by@comfyanonymous in#12095
• Add RoPE Position Adjustment for Small Grid IC-LoRA by@tavihalperin in#12074
• [API Nodes] remove ByteDanceImageEditNode node (seededit) by@bigcat88 in#12069
• [API Nodes] add Magnific nodes by@bigcat88 in#11986
• Fix Noise_EmptyNoise when using nested latents by@kijai in#12089
• wan-vae: Switch off feature cache for single frame by@rattus128 in#12090
• Update amd portable for rocm 7.2 by@comfyanonymous in#12101
• Update workflow templates to v0.8.23 by@comfyui-wiki in#12102
• Update workflow templates to v0.8.24 by@comfyui-wiki in#12103

New Contributors

• @izorinLightricks made their first contribution in#11990
• @gitmylo made their first contribution in#11991
• @markuryy made their first contribution in#11997
• @maromri made their first contribution in#11966

Full Changelog:v0.10.0...v0.11.0

Contributors