v0.15.1

What's Changed

• Fix KeyError when prompt entries lack class_type key by @Kosinkadink in #12595
• comfy aimdo 0.2.1 by @rattus128 in #12620
• Disable dynamic_vram when using torch compiler by @rattus128 in #12612
• Fix Aimdo fallback on probe to not use zero-copy sft by @rattus128 in #12634
• comfy aimdo 0.2.2 by @rattus128 in #12635
• Patch frontend to 1.39.19 (from 1.39.16) (fix progress text serialization in API nodes) by @christian-byrne in #12642
• Fix LTXAV text enc min length. by @comfyanonymous in #12640
• Fix ltxav te mem estimation. by @comfyanonymous in #12643
• feat: Support WanVideo based segmentation model FlowRVS by @kijai in #12637
• feat: per-guide attention strength control in self-attention by @tavihalperin in #12518
• Cleanups to the last PR. by @comfyanonymous in #12646
• fix: move essentials_category to correct replacement nodes by @christian-byrne in #12568
• Fix GLSL node with pyopengl accelerate numpy textures by @pythongosssss in #12650
• main: load aimdo earlier by @rattus128 in #12655
• feat(api-nodes): add NanoBanana2 by @bigcat88 in #12660
• Update workflow templates to v0.9.4 by @comfyui-wiki in #12664

Full Changelog: v0.15.0...v0.15.1

v0.15.0

What's Changed

• ops: limit return of requants (Fix perf of some fp8 dynamic_vram workflows) by @rattus128 in #12506
• Bump comfyui-frontend-package to 1.39.14 by @comfy-pr-bot in #12494
• BBox widget by @jtydhr88 in #11594
• fix: use glob matching for Gemini image MIME types by @huntcsg in #12511
• fix(api-nodes): add price badge for Rodin Gen-2 node by @bigcat88 in #12512
• Add simple 3 band equalizer node for audio. by @comfyanonymous in #12519
• feat: Add basic text generation support with native models, initially supporting Gemma3 by @kijai in #12392
• fix(api-nodes): force Gemini to return uncompressed images by @bigcat88 in #12516
• feat: add essentials_category by @Yourz in #12357
• feat: mark 429 widgets as advanced for collapsible UI by @christian-byrne in #12197
• Small cleanup and try to get qwen 3 work with the text gen. by @comfyanonymous in #12537
• Force min length 1 when tokenizing for text generation. by @comfyanonymous in #12538
• Add GLSL shader node using PyOpenGL by @pythongosssss in #12148
• [API Nodes] add ElevenLabs nodes by @bigcat88 in #12207
• chore: add CodeRabbit configuration for automated code review by @christian-byrne in #12539
• Update nightly installation command for ROCm by @comfyanonymous in #12547
• Fix non-contiguous audio waveform crash in video save by @artokun in #12550
• feat: add gradient-slider display mode for FLOAT inputs by @jtydhr88 in #12536
• update glsl blueprint with gradient by @jtydhr88 in #12548
• feat: add essential subgraph blueprints by @christian-byrne in #12552
• fix: swap essentials_category from CLIPTextEncode to PrimitiveStringM… by @christian-byrne in #12553
• Add support for pyopengl < 3.1.4 where the size parameter does not exist by @pythongosssss in #12555
• comfy-aimdo 0.2 - Improved pytorch allocator integration by @rattus128 in #12557
• fix: specify UTF-8 encoding when reading subgraph files by @DrJKL in #12563
• Add category to Normalized Attention Guidance node by @christian-byrne in #12565
• chore: tune CodeRabbit config to limit review scope and disable for drafts by @christian-byrne in #12567
• Move LTXAV av embedding connectors to diffusion model. by @comfyanonymous in #12569
• Fix dtype issue in embeddings connector. by @comfyanonymous in #12570
• Fix issue loading fp8 ltxav checkpoints. by @comfyanonymous in #12582
• feat(api-nodes): add KlingAvatar node by @bigcat88 in #12591
• Update workflow templates to v0.9.2 by @comfyui-wiki in #12596
• Add SplitImageToTileList and ImageMergeTileList nodes. by @comfyanonymous in #12599
• Temporality unbreak some LTXAV (LTX 2.0) workflows to give people time to migrate. by @comfyanonymous in #12605
• Patch frontend to 1.39.16 (from 1.39.14) by @christian-byrne in #12604
• feat(api-nodes): add ByteDance Seedream-5 model by @bigcat88 in #12609
• Update workflow templates to v0.9.3 by @comfyui-wiki in #12610
• Don't crash right away if op is uninitialized. by @comfyanonymous in #12615
• Update embedded docs to v0.4.3 by @comfyui-wiki in #12601

New Contributors

• @huntcsg made their first contribution in #12511
• @Yourz made their first contribution in #12357
• @artokun made their first contribution in #12550

Full Changelog: v0.14.1...v0.15.0

v0.14.2

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

v0.14.1

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

v0.14.0

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

v0.13.0

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

v0.12.3

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

v0.12.2

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

v0.12.1

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

v0.12.0

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