880 Commits

Author	SHA1	Message	Date
John Pollock	40bf50b32c	Revert "Add tiled VAE lane to MultiGPU Work Units" ... This reverts commit 4d3d68e473. The tiled VAE lane will land as part of a follow-up PR alongside the UPSCALE_MODEL lane, separated from the threaded-loader fix PR (#14052) to keep the upstream merge focused.	2026-05-22 16:37:10 -07:00
John Pollock	4d3d68e473	Add tiled VAE lane to MultiGPU Work Units	2026-05-22 13:42:21 -05:00
John Pollock	74b0a826ea	Add UPSCALE_MODEL lane to MultiGPU CFG Split ... Introduce tiled_scale_multidim_multigpu in comfy/utils.py: a tile scheduler that dispatches per-device tile functions through the existing MultiGPUThreadPool and merges per-device CPU output buffers in deterministic key order. The worker only catches BaseException at the thread boundary to funnel errors to the main thread; bare torch.cuda.set_device and torch.cuda.synchronize calls inside the worker fail loud if the device is not CUDA, which is part of the primitive's contract. Add UPSCALE_MODEL input on the MultiGPU CFG Split node and an upscale-model descriptor deepclone helper in comfy/multigpu.py. Clones stay CPU-resident until execute time and are returned to CPU afterward. ImageUpscaleWithModel dispatches through tiled_scale_multidim_multigpu when a multigpu descriptor is attached; the single-device path runs unchanged when no clones are present.	2026-05-22 13:41:48 -05:00
Kosinkadink	d0b9dbb5a6	Merge remote-tracking branch 'origin/master' into worksplit-multigpu ... Brings in 18 commits from master so worksplit-multigpu does not regress fixes that landed on main since the last sync: - #13699 Hunyuan 3D 2.1 batch-size fixes (overlap with our own backport; conflict resolved in favor of the shape>=2 gate that binds swap_cfg_halves once and reuses it for the output swap-back) - #14031 ModelPatcherDynamic lora reshape / backup restore fix - #13802 Multi-threaded model load (memory_management / pinned_memory / model_management / aimdo plumbing) - #12679 lanczos single-channel tensor fix - #14010 Stable Audio 3 support - assorted partner-node, openapi, workflow-template, and tooling updates Amp-Thread-ID: https://ampcode.com/threads/T-019e4a00-fe3d-76bd-a2f2-a8c8c4040082 Co-authored-by: Amp <amp@ampcode.com>	2026-05-21 12:17:59 -07:00
Alexis Rolland	4259a0c7c3	Update MoGe nodes display names, search aliases and descriptions (#14030)	2026-05-21 16:50:09 +08:00
Alexis Rolland	af3d9b60af	chore: Dataset nodes clean-up (CORE-237) (#14002)	2026-05-21 15:14:16 +08:00
Alexis Rolland	7b7c5fed7c	Update MediaPipe nodes to standardize with existing code base (CORE-242) (#14025)	2026-05-21 14:39:30 +08:00
Jedrzej Kosinski	4d9106dced	Document --cuda-device comma format and MultiGPU Options relative_speed gap ... Two doc-only changes addressing minor CodeRabbit findings on PR #7063: * cli_args.py: clarify --cuda-device help text to document the required comma-separated format ('0' or '0,1'), matching how the value is consumed by CUDA_VISIBLE_DEVICES in main.py. * nodes_multigpu.py: add a docstring NOTE on the (currently unregistered) MultiGPUOptionsNode explaining that its relative_speed input is plumbed through to model_options['multigpu_options'] but is not yet consulted by the cond scheduler, which still uses uniform round-robin via next_available_device(). Wire relative_speed into the scheduler before re-enabling the node. Amp-Thread-ID: https://ampcode.com/threads/T-019e43b8-8258-70fd-ab3a-53e4c97f85d5 Co-authored-by: Amp <amp@ampcode.com>	2026-05-20 20:48:59 -07:00
Jedrzej Kosinski	50d1dd6273	Fix MultiGPU Options node discarding cloned GPUOptionsGroup ... GPUOptionsGroup.clone() returns a new instance, but the return value was discarded, causing the node to mutate the upstream caller's group in-place. When multiple MultiGPU Options nodes share an input group, each node's additions would leak into earlier siblings. Assign the clone result back to gpu_options so each node owns its own copy. Amp-Thread-ID: https://ampcode.com/threads/T-019e43b8-8258-70fd-ab3a-53e4c97f85d5 Co-authored-by: Amp <amp@ampcode.com>	2026-05-20 16:46:23 -07:00
Jukka Seppänen	4d6a058bf1	feat: MediaPipe face detection (CORE-235) (#14009) ... * Initial mediapipe face detection support * Update face_geometry.py * Account for diff sized batch input * Model folder placeholder	2026-05-20 16:07:48 -07:00
Jedrzej Kosinski	ff766e5cfa	Merge remote-tracking branch 'origin/master' into merge-master-into-worksplit-multigpu ... Amp-Thread-ID: https://ampcode.com/threads/T-019e4352-d45e-75bc-8ed7-ed3a7f6d129a Co-authored-by: Amp <amp@ampcode.com> # Conflicts: # comfy/ldm/sam3/detector.py # comfy/ldm/sam3/tracker.py # comfy/model_base.py # comfy/quant_ops.py # comfy/supported_models.py # comfy_api_nodes/apis/bytedance.py # comfy_api_nodes/nodes_bytedance.py # comfy_api_nodes/nodes_openai.py # comfy_extras/frame_interpolation_models/film_net.py # comfy_extras/frame_interpolation_models/ifnet.py # comfy_extras/nodes_ace.py # comfy_extras/nodes_frame_interpolation.py # comfy_extras/nodes_lt_audio.py # comfy_extras/nodes_sam3.py # comfy_extras/nodes_video_model.py # folder_paths.py # nodes.py # requirements.txt	2026-05-19 21:43:51 -07:00
comfyanonymous	72e3f6081c	Add downscale ratio to empty ltxv latent. (#13999)	2026-05-19 20:28:06 -07:00
Pauan	7ec7b6ffe9	Adding new StringFormat node (#13997)	2026-05-20 10:25:49 +08:00
comfyanonymous	a4382e056e	Use temporal downscale to make empty audio latent nodes more reusable. (#13975)	2026-05-19 00:14:30 -04:00
Alexis Rolland	d71cc1c8f2	chore: Various QoL updates of nodes display names, descriptions and categories (CORE-190, CORE-191) (#13830) ... * Move detection category under image category * Add missing categories * Move detection nodes to detection category * Move save nodes to image root catefory * Rename postprocessors * Move mask category under image * Move guiders category to parent level at root of sampling category * Move custom_sampling category to parent level at the root of sampling category * Modify description of LoRA loaders * Fix node id SolidMask * Move VOID Quadmask under image/mask * Group compositing nodes under image/compositing * Move load image as mask to image category for consistency with other load image nodes * Align display name with Load Checkpoint * Move dataset category under training category * Rename Number Convert to Conver Number (verb first) * Rename Canny node * Revert wanBlockSwap + description * Add description to RemoveBackground node * Revert category update of dataset	2026-05-19 00:13:48 -04:00
comfyanonymous	990a7ae7f2	Initial work to make downscale_ratio_temporal work. (#13972)	2026-05-18 23:01:43 -04:00
Jedrzej Kosinski	df2454b47e	Reduce min for Batch Image/Mask/Latent nodes from 2 to 1 (#13721)	2026-05-19 09:50:14 +08:00
drozbay	292814c31e	feat: Add optional attention_mask input to LTXVAddGuide (CORE-220) (#13965)	2026-05-19 05:07:04 +08:00
rattus	16f862f02a	implement dynamic clip saving (#13959) ... Fix clip saving by doing the same patching process and diffusion models.	2026-05-18 11:46:40 -07:00
Alvin Tang	d4c6c9eff8	fix(FeatherMask): correct negative zero indexing for right/bottom feathering (#12881)	2026-05-18 20:22:15 +08:00
drozbay	d3607a8e6d	feat: Add downscaled IC-LoRA support to LTXVAddGuide (CORE-102) (#13896)	2026-05-16 15:02:57 +08:00
Jukka Seppänen	33ce449c8b	Reduce LTX2.3 peak VRAM when guide_mask is in use (CORE-166) (#13735) ... - Reduce peak VRAM by handling self_attn_mask more efficiently - Fallback to SDPA when self_attention_mask is used	2026-05-16 00:02:27 +03:00
drozbay	04856acc69	Allow negative batch_index on ImageFromBatch and LatentFromBatch (CORE-195) (#13857)	2026-05-15 22:30:02 +08:00
Jukka Seppänen	77e2ed5e01	feat: Support MoGe (CORE-168) (#13878)	2026-05-15 10:34:56 +08:00
Jukka Seppänen	b2000029c8	Persists ModelNoiseScale when also patching shift (#13892)	2026-05-14 18:36:17 -07:00
Jukka Seppänen	1f28908d6e	Make audio processing nodes handle None -inputs (#13879)	2026-05-14 10:51:35 +08:00
Jukka Seppänen	8505abf52e	feat: Extend Save3D to save vertex colors and textures (CORE-189) (#13824) ... Split GLB save logic out of nodes_hunyuan3d.py into a new nodes_save_3d.py, and extend the writer to support UVs, per-vertex colors, and embedded baseColor textures. Extend the MESH type with optional uvs, vertex_colors, and texture fields so meshes can carry texture data through the graph. Add pack_variable_mesh_batch / get_mesh_batch_item helpers and switch VoxelToMesh / VoxelToMeshBasic to use them so batches with differing vertex/face counts no longer fail at torch.stack.	2026-05-13 18:33:53 +03:00
AustinMroz	a5189fed51	Add Create Video to the essentials tab (#13863)	2026-05-13 14:42:31 +08:00
angad777	cccb697aa3	fix: create input directory if missing in LoadAudio define_schema (#13834)	2026-05-13 10:41:07 +08:00
comfyanonymous	300b6c8c91	Revert some breaking changes. (#13861)	2026-05-12 17:28:20 -07:00
drozbay	1d95ed211e	Fix LTXV mid-video multi-frame guide alignment (CORE-129) (#13625)	2026-05-13 06:57:31 +08:00
Jukka Seppänen	8e53f001a4	feat: Support HiDream-O1-Image (CORE-187) (#13817) ... * Initial HiDream01-image support * Cleanup nodes * Cleaner handling of empty placeholder models * Remove snap_to_predefined, prefer tooltip for the trained resolutions * Add model and block wrappers * Fix shift tooltip * Add node to work around the patch tile issue Experimental, runs multiple passes with the patch grid offset and blends with various different methods. * Qwen35 vision rotary_pos_emb cast fix * Fix embedding layout type * Some small optimizations * Cleanup, don't need this fallback * Prefix KV cache, cleanup Bit of speed, reduce redundant code * Get rid of redundant custom sampler, refactor noise scaling Our existing lcm sampler is mathematically same, just added the missing options to it instead and a node to control them. Refactored the noise scaling and fix it for the stochastic samplers, add a generic node to control the initial noise scale. * Update nodes_hidream_o1.py * Fix some cache validation cases * Keep existing sampling params * Remove redundant video vision path * Replace some numpy ops with torch * Fx RoPE index for batch size > 1 * Prefer torch preprocessing * Rename block_type to be compatible with existing patch nodes * Fixes and tweaks	2026-05-11 20:35:53 -07:00
Daxiong (Lin)	1eeaf23f20	Remove advanced flag from layers input in EmptyQwenImageLayeredLatentImage node (#13823)	2026-05-11 01:23:04 +08:00
LaVie024	95f6652ef5	Add Boolean support to Math Expression Node (#13224) ... * Add Boolean support to math expressions * Change boolean result test to assert values --------- Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>	2026-05-10 15:33:47 +08:00
comfyanonymous	20f5e474da	Use LatentCutToBatch instead. (#13815) ... Removed VAEDecodeVideoFramewise from nodes_wandancer.py.	2026-05-09 14:17:00 -07:00
Jukka Seppänen	3200f28e3a	Support Wan-Dancer (#13813) ... * initial WanDancer support * nodes_wandancer: Add list form of chunker. Create an alternate list form of the node so the chunk gens can be trivially looped by the comfy executor. * Closer match to original soxr resampling * Remove librosa node * Cleanup --------- Co-authored-by: Rattus <rattus128@gmail.com>	2026-05-09 14:02:56 -07:00
Alexis Rolland	c5ecd231a2	fix: Fix bug when mask not on same device (CORE-181) (#13801)	2026-05-08 23:06:29 +08:00
drozbay	9864f5ac86	fix: Stop LTXVImgToVideoInplace from mutating input latents and dropping noise_mask (#13793)	2026-05-08 23:02:17 +08:00
drozbay	05cd076bc1	fix: Make LTXVAddGuide center-crop guide images to match other LTXV nodes (#13794)	2026-05-08 22:48:59 +08:00
Yousef R. Gamaleldin	d3c18c1636	Add support for BiRefNet background remove model (CORE-46) (#12747)	2026-05-08 17:59:24 +08:00
omahs	bac6fc35fb	Fix typos (#10986)	2026-05-08 17:14:45 +08:00
Alexis Rolland	594de378fe	Update nodes categories and display names (CORE-89) (#13786)	2026-05-08 01:02:55 -04:00
Talmaj	ef8f25601a	Add I2V for causal forcing model. (#13719)	2026-05-07 18:38:36 -07:00
Jukka Seppänen	8dc3f3f209	Improve SAM3 large input handling (#13767)	2026-05-07 17:18:28 -07:00
Alexis Rolland	a61e2bbb85	Add device selection on Image Only Load Checkpoint (CORE-158) (#13748) ... * Add device selection on Image Only Load Checkpoint * Rename variables * Update variable name * Fix linting	2026-05-06 21:49:23 -07:00
Talmaj	78b3096bf3	Void model - pass 1 & 2 (CORE-38) (#13403)	2026-05-05 19:59:04 -07:00
iChrist	160b95f75c	Update language options in nodes_ace.py (#12578) ... * Update language options in nodes_ace.py Modified it to include all 51 language options ace-step1.5 supports instead of the original 23 comfyui had. * re-arrange list by popularity changed order of the languages to be ordered by popularity en is default unknown is last * Update comfy_extras/nodes_ace.py	2026-05-05 19:47:57 -07:00
drozbay	e5369c0eec	feat: Context windows - add causal_window_fix to improve blending of context windows (CORE-100) (#13563) ... * Context windows: add causal_window_fix toggle * Fix slice_cond to correctly handle causal anchor index for temporal offsets	2026-05-05 16:40:53 -07:00
drozbay	41d73ad180	fix(audio): drop sample_rate key from LTXVEmptyLatentAudio (CORE-157) (#13716)	2026-05-05 11:33:16 -07:00
Alexis Rolland	639f631a08	chore: Update display names and categories for text nodes (CORE-155) (#13712)	2026-05-05 22:31:24 +08:00