4633 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Deep Mehta	0141af0786	refactor: rename _is_cacheable_value to _is_external_cacheable_value ... Clearer name since objects are also cached locally - this specifically checks for external caching eligibility. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-30 00:46:10 +05:30
Deep Mehta	0440ebcf6e	feat: add optional ui field to CacheValue ... - Add ui field to CacheValue dataclass (default None) - Pass ui when creating CacheValue for external providers - Use result.ui (or default {}) when returning from external cache lookup This allows external cache implementations to store/retrieve UI data if desired, while remaining optional for implementations that skip it. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-29 20:22:04 +05:30
Deep Mehta	4afa80dc07	docs: make should_cache docstring implementation-agnostic ... Remove prescriptive filtering suggestions - let implementations decide their own caching logic based on their use case. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-29 19:52:06 +05:30
Deep Mehta	d755f7ca19	docs: clarify should_cache filtering criteria ... Change docstring from "Skip large values" to "Skip if download time > compute time" which better captures the cost/benefit tradeoff for external caching. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-29 19:50:12 +05:30
Deep Mehta	2049066cff	refactor: expose CacheProvider API via comfy_api.latest.Caching ... - Add Caching class to comfy_api/latest/__init__.py that re-exports from comfy_execution.cache_provider (source of truth) - Fix docstring: "Skip large values" instead of "Skip small values" (small compute-heavy values are good cache targets) - Maintain backward compatibility: comfy_execution.cache_provider imports still work Usage: from comfy_api.latest import Caching class MyProvider(Caching.CacheProvider): def on_lookup(self, context): ... def on_store(self, context, value): ... Caching.register_provider(MyProvider()) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-29 19:42:34 +05:30
Deep Mehta	9b0ca8b95c	Merge remote-tracking branch 'origin/master' into feat/cache-provider-api	2026-01-28 13:30:03 +05:30
comfyanonymous	4f5bd39b1c	Update Python 3.14 compatibility notes in README (#12127)	2026-01-27 19:58:48 -05:00
guill	dcff27fe3f	Add support for dev-only nodes. (#12106) ... When a node is declared as dev-only, it doesn't show in the default UI unless the dev mode is enabled in the settings. The intention is to allow nodes related to unit testing to be included in ComfyUI distributions without confusing the average user.	2026-01-27 13:03:29 -08:00
comfyanonymous	09725967cf	ComfyUI version v0.11.0	2026-01-26 23:08:01 -05:00
ComfyUI Wiki	5f62440fbb	chore: update workflow templates to v0.8.24 (#12103)	2026-01-26 22:47:33 -05:00
ComfyUI Wiki	ac91c340f4	Update workflow templates to v0.8.23 (#12102)	2026-01-26 21:39:39 -05:00
comfyanonymous	2db3b0ff90	Update amd portable for rocm 7.2 (#12101) ... * Update amd portable for rocm 7.2 * Update Python patch version in release workflow	2026-01-26 19:49:31 -05:00
rattus	6516ab335d	wan-vae: Switch off feature cache for single frame (#12090) ... The code throughout is None safe to just skip the feature cache saving step if none. Set it none in single frame use so qwen doesn't burn VRAM on the unused cache.	2026-01-26 19:40:19 -05:00
Jukka Seppänen	ad53e78f11	Fix Noise_EmptyNoise when using nested latents (#12089)	2026-01-26 19:25:00 -05:00
Alexander Piskun	29011ba87e	[API Nodes] add Magnific nodes (#11986) ... * feat(api-nodes): add Magnific nodes * aggressive downscaling should not be performed * disable upscaler nodes --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-01-26 14:10:09 -08:00
Alexander Piskun	cd4985e2f3	chore(api-nodes): remove ByteDanceImageEditNode node (seededit) (#12069) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-01-26 13:58:33 -08:00
Tavi Halperin	bfe31d0b9d	IC-LoRA: support small grid (#12074)	2026-01-26 15:33:19 -05:00
comfyanonymous	2129e7d278	Fix mistral 3 tokenizer code failing on latest transformers version and other breakage. (#12095) ... * Fix mistral 3 tokenizer code failing on latest transformers version. * Add requests to the requirements	2026-01-26 11:39:00 -05:00
comfyanonymous	7ee77ff038	Add name to LoraLoaderModelOnly. (#12078)	2026-01-25 21:01:55 -05:00
comfyanonymous	26c5bbb875	Move nodes from previous PR into their own file. (#12066)	2026-01-24 23:02:32 -05:00
Kohaku-Blueleaf	a97c98068f	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) ... * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	2026-01-24 22:56:22 -05:00
comfyanonymous	635406e283	Only enable fp16 on z image models that actually support it. (#12065)	2026-01-24 22:32:28 -05:00
pythongosssss	ed6002cb60	add support for kwargs inputs to allow arbitrary inputs from frontend (#12063) ... used to output selected combo index Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-01-24 17:30:40 -08:00
Alexander Piskun	bc72d7f8d1	[API Nodes] add TencentHunyuan3D nodes (#12026) ... * feat(api-nodes): add TencentHunyuan3D nodes * add "(Pro)" to display name --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-01-24 17:10:09 -08:00
comfyanonymous	aef4e13588	Make empty latent node work with other models. (#12062)	2026-01-24 19:23:20 -05:00
Deep Mehta	dcf686857c	fix: use hashable types in frozenset test and add dict test ... Frozensets can only contain hashable types, so use nested frozensets instead of dicts. Added separate test for dict handling via serialize_cache_key. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-24 15:47:53 +05:30
Deep Mehta	17eed38750	fix: move _torch_available before usage and use importlib.util.find_spec ... Fixes ruff F821 (undefined name) and F401 (unused import) errors. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-24 15:34:29 +05:30
Deep Mehta	f4623c0e1b	style: remove unused imports in test_cache_provider.py ... 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-24 14:25:00 +05:30
Deep Mehta	5e4bbca1ad	test: add unit tests for CacheProvider API ... - Add comprehensive tests for _canonicalize deterministic ordering - Add tests for serialize_cache_key hash consistency - Add tests for contains_nan utility - Add tests for estimate_value_size - Add tests for provider registry (register, unregister, clear) - Move json import to top-level (fix inline import) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-24 14:20:49 +05:30
Deep Mehta	e17571d9be	fix: use deterministic hash for cache keys instead of pickle ... Pickle serialization is NOT deterministic across Python sessions due to hash randomization affecting frozenset iteration order. This causes distributed caching to fail because different pods compute different hashes for identical cache keys. Fix: Use _canonicalize() + JSON serialization which ensures deterministic ordering regardless of Python's hash randomization. This is critical for cross-pod cache key consistency in Kubernetes deployments. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-24 14:07:46 +05:30
rattus	4e6a1b66a9	speed up and reduce VRAM of QWEN VAE and WAN (less so) (#12036) ... * ops: introduce autopad for conv3d This works around pytorch missing ability to causal pad as part of the kernel and avoids massive weight duplications for padding. * wan-vae: rework causal padding This currently uses F.pad which takes a full deep copy and is liable to be the VRAM peak. Instead, kick spatial padding back to the op and consolidate the temporal padding with the cat for the cache. * wan-vae: implement zero pad fast path The WAN VAE is also QWEN where it is used single-image. These convolutions are however zero padded 3d convolutions, which means the VAE is actually just 2D down the last element of the conv weight in the temporal dimension. Fast path this, to avoid adding zeros that then just evaporate in convoluton math but cost computation.	2026-01-23 19:56:14 -05:00
comfyanonymous	9cf299a9f9	Make regular empty latent node work properly on flux 2 variants. (#12050)	2026-01-23 19:50:48 -05:00
ComfyUI Wiki	e89b22993a	Support ModelScope-Trainer/DiffSynth LoRA format for Flux.2 Klein models (#12042)	2026-01-23 15:27:49 -05:00
Jukka Seppänen	55bd606e92	LTX2: Refactor forward function for better VRAM efficiency and fix spatial inpainting (#12046) ... * Disable timestep embed compression when inpainting Spatial inpainting not compatible with the compression * Reduce crossattn peak VRAM * LTX2: Refactor forward function for better VRAM efficiency	2026-01-23 15:26:38 -05:00
Christian Byrne	79cdbc81cb	feat: Improve ResizeImageMaskNode UX with tooltips and search aliases (#12040) ... - Add search_aliases for discoverability: resize, scale, dimensions, etc. - Add node description for hover tooltip - Add tooltips to all inputs explaining their behavior - Reorder options: most common (scale dimensions) first, most technical (scale to multiple) last Addresses user feedback that 'resize' search returned nothing useful and options like 'match size' and 'scale to multiple' were not self-explanatory.	2026-01-22 22:04:27 -08:00
comfyanonymous	f443b9f2ca	Revert "feat: Improve ResizeImageMaskNode UX with tooltips and search aliases…" (#12038) ... This reverts commit 4e3038114a.	2026-01-22 23:02:37 -05:00
Christian Byrne	4e3038114a	feat: Improve ResizeImageMaskNode UX with tooltips and search aliases (#12013) ... - Add search_aliases for discoverability: resize, scale, dimensions, etc. - Add node description for hover tooltip - Add tooltips to all inputs explaining their behavior - Reorder options: most common (scale dimensions) first, most technical (scale to multiple) last Addresses user feedback that 'resize' search returned nothing useful and options like 'match size' and 'scale to multiple' were not self-explanatory.	2026-01-22 18:46:55 -08:00
Christian Byrne	bbb8864778	add search aliases to all nodes (#12035) ... * feat: Add search_aliases field to node schema Adds `search_aliases` field to improve node discoverability. Users can define alternative search terms for nodes (e.g., "text concat" → StringConcatenate). Changes: - Add `search_aliases: list[str]` to V3 Schema - Add `SEARCH_ALIASES` support for V1 nodes - Include field in `/object_info` response - Add aliases to high-priority core nodes V1 usage: ```python class MyNode: SEARCH_ALIASES = ["alt name", "synonym"] ``` V3 usage: ```python io.Schema( node_id="MyNode", search_aliases=["alt name", "synonym"], ... ) ``` ## Related PRs - Frontend: Comfy-Org/ComfyUI_frontend#XXXX (draft - merge after this) - Docs: Comfy-Org/docs#XXXX (draft - merge after stable) * Propagate search_aliases through V3 Schema.get_v1_info to NodeInfoV1 * feat: add SEARCH_ALIASES for core nodes (#12016) Add search aliases to 22 core nodes in nodes.py to improve node discoverability: - Checkpoint/model loaders: CheckpointLoader, DiffusersLoader - Conditioning nodes: ConditioningAverage, ConditioningSetArea, ConditioningSetMask, ConditioningZeroOut - Style nodes: StyleModelApply - Image nodes: LoadImageMask, LoadImageOutput, ImageBatch, ImageInvert, ImagePadForOutpaint - Latent nodes: LoadLatent, SaveLatent, LatentBlend, LatentComposite, LatentCrop, LatentFlip, LatentFromBatch, LatentUpscale, LatentUpscaleBy, RepeatLatentBatch * feat: add SEARCH_ALIASES for image, mask, and string nodes (#12017) Add search aliases to nodes in comfy_extras for better discoverability: - nodes_mask.py: mask manipulation nodes - nodes_images.py: image processing nodes - nodes_post_processing.py: post-processing effect nodes - nodes_string.py: string manipulation nodes - nodes_compositing.py: compositing nodes - nodes_morphology.py: morphological operation nodes - nodes_latent.py: latent space nodes Uses search_aliases parameter in io.Schema() for v3 nodes. * feat: add SEARCH_ALIASES for audio and video nodes (#12018) Add search aliases to audio and video nodes for better discoverability: - nodes_audio.py: audio loading, saving, and processing nodes - nodes_video.py: video loading and processing nodes - nodes_wan.py: WAN model nodes Uses search_aliases parameter in io.Schema() for v3 nodes. * feat: add SEARCH_ALIASES for model and misc nodes (#12019) Add search aliases to model-related and miscellaneous nodes: - Model nodes: nodes_model_merging.py, nodes_model_advanced.py, nodes_lora_extract.py - Sampler nodes: nodes_custom_sampler.py, nodes_align_your_steps.py - Control nodes: nodes_controlnet.py, nodes_attention_multiply.py, nodes_hooks.py - Training nodes: nodes_train.py, nodes_dataset.py - Utility nodes: nodes_logic.py, nodes_canny.py, nodes_differential_diffusion.py - Architecture-specific: nodes_sd3.py, nodes_pixart.py, nodes_lumina2.py, nodes_kandinsky5.py, nodes_hidream.py, nodes_fresca.py, nodes_hunyuan3d.py - Media nodes: nodes_load_3d.py, nodes_webcam.py, nodes_preview_any.py, nodes_wanmove.py Uses search_aliases parameter in io.Schema() for v3 nodes, SEARCH_ALIASES class attribute for legacy nodes.	2026-01-22 18:36:58 -08:00
Omri Marom	d7f3241bf6	qwen_image: propagate attention mask. (#11966)	2026-01-22 20:02:31 -05:00
comfyanonymous	09a2e67151	Support loading flux 2 klein checkpoints saved with SaveCheckpoint. (#12033)	2026-01-22 18:20:48 -05:00
rattus	0fd1b78736	Reduce LTX2 VAE VRAM consumption (#12028) ... * causal_video_ae: Remove attention ResNet This attention_head_dim argument does not exist on this constructor so this is dead code. Remove as generic attention mid VAE conflicts with temporal roll. * ltx-vae: consoldate causal/non-causal code paths * ltx-vae: add cache rolling adder * ltx-vae: use cached adder for resnet * ltx-vae: Implement rolling VAE Implement a temporal rolling VAE for the LTX2 VAE. Usually when doing temporal rolling VAEs you can just chunk on time relying on causality and cache behind you as you go. The LTX VAE is however non-causal. So go whole hog and implement per layer run ahead and backpressure between the decoder layers using recursive state beween the layers. Operations are ammended with temporal_cache_state{} which they can use to hold any state then need for partial execution. Convolutions cache their inputs behind the up to N-1 frames, and skip connections need to cache the mismatch between convolution input and output that happens due to missing future (non-causal) input. Each call to run_up() processes a layer accross a range on input that may or may not be complete. It goes depth first to process as much as possible to try and digest frames to the final output ASAP. If layers run out of input due to convolution losses, they simply return without action effectively applying back-pressure to the earlier layers. As the earlier layers do more work and caller deeper, the partial states are reconciled and output continues to digest depth first as much as possible. Chunking is done using a size quota rather than a fixed frame length and any layer can initiate chunking, and multiple layers can chunk at different granulatiries. This remove the old limitation of always having to process 1 latent frame to entirety and having to hold 8 full decoded frames as the VRAM peak.	2026-01-22 16:54:18 -05:00
Terry Jia	8490eedadf	add ply & 3dgs format in 3d node (#11474)	2026-01-22 09:46:56 -08:00
Alexander Piskun	72f6be1690	chore(api-nodes): rename BriaImage and OpenAIGImage nodes (#12022)	2026-01-21 23:42:04 -08:00
Jukka Seppänen	16b9aabd52	Support Multi/InfiniteTalk (#10179) ... * re-init * Update model_multitalk.py * whitespace... * Update model_multitalk.py * remove print * this is redundant * remove import * Restore preview functionality * Move block_idx to transformer_options * Remove LoopingSamplerCustomAdvanced * Remove looping functionality, keep extension functionality * Update model_multitalk.py * Handle ref_attn_mask with separate patch to avoid having to always return q and k from self_attn * Chunk attention map calculation for multiple speakers to reduce peak VRAM usage * Update model_multitalk.py * Add ModelPatch type back * Fix for latest upstream * Use DynamicCombo for cleaner node Basically just so that single_speaker mode hides mask inputs and 2nd audio input * Update nodes_wan.py	2026-01-21 23:09:48 -05:00
Jukka Seppänen	245f6139b6	More targeted embedding_connector loading for LTX2 text encoder (#11992) ... Reduces errors	2026-01-21 23:05:06 -05:00
Jukka Seppänen	3365ad18a5	Support LTX2 tiny vae (taeltx_2) (#11929)	2026-01-21 23:03:51 -05:00
Jedrzej Kosinski	f09904720d	Fix for edge case of EasyCache when conditionings change during a sampling run (like with timestep scheduling) (#12020)	2026-01-21 23:01:35 -05:00
comfyanonymous	abe2ec26a6	Support the Anima model. (#12012)	2026-01-21 19:44:28 -05:00
Christian Byrne	bdeac8897e	feat: Add search_aliases field to node schema (#12010) ... * feat: Add search_aliases field to node schema Adds `search_aliases` field to improve node discoverability. Users can define alternative search terms for nodes (e.g., "text concat" → StringConcatenate). Changes: - Add `search_aliases: list[str]` to V3 Schema - Add `SEARCH_ALIASES` support for V1 nodes - Include field in `/object_info` response - Add aliases to high-priority core nodes V1 usage: ```python class MyNode: SEARCH_ALIASES = ["alt name", "synonym"] ``` V3 usage: ```python io.Schema( node_id="MyNode", search_aliases=["alt name", "synonym"], ... ) ``` ## Related PRs - Frontend: Comfy-Org/ComfyUI_frontend#XXXX (draft - merge after this) - Docs: Comfy-Org/docs#XXXX (draft - merge after stable) * Propagate search_aliases through V3 Schema.get_v1_info to NodeInfoV1	2026-01-21 15:36:02 -08:00
Alexander Piskun	451af70154	fix(api-nodes-Vidu): allow passing up to 7 subjects in Vidu Reference node (#12002)	2026-01-21 04:03:45 -08:00