5247 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Emiliooooo12	f44b7fbbc9	Merge 61235fc35a into 264b003286	2026-05-18 17:49:14 +08:00
Alexander Piskun	264b003286	[Partner Nodes] fix Opus 4.7 sending deprecated temperature parameter (#13955)	2026-05-18 09:53:31 +03:00
Jukka Seppänen	971c9e3518	HiDream-O1: support area conditioning (#13944)	2026-05-18 01:17:05 -04:00
Jukka Seppänen	b39af210d0	Fix Qwen3.5 text generation with multiple input images (#13943)	2026-05-18 01:16:42 -04:00
apophis	aeadb7acaa	correct OOM format (#13950)	2026-05-18 12:06:45 +08:00
comfyanonymous	f48d2a017e	Log which quant ops are enabled/emulated. (#13946)	2026-05-17 16:30:54 -04:00
comfyanonymous	7c4d95d1bc	Enhance README with application and cloud links (#13936)	2026-05-16 23:55:43 -04:00
drozbay	d3607a8e6d	feat: Add downscaled IC-LoRA support to LTXVAddGuide (CORE-102) (#13896)	2026-05-16 15:02:57 +08:00
comfyanonymous	5d5a4554e1	Remove useless option and clarify what lowvram does. (#13922)	2026-05-15 17:59:02 -07:00
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
Emiliooooo	61235fc35a	fix(directml): replace try/except with device-type guard; fix both ZeroDivisionError sites ... Improves on the previous directml commit with three research-based refinements: 1. model_management.py — module_mmap_residency() and cast_to_gathered() Replace broad try/except NotImplementedError with an explicit `t.device.type == 'privateuseone'` guard. Checking device type is faster in a hot loop and makes the intent self-documenting. Fixes: github.com/Comfy-Org/ComfyUI/issues/8347 2. attention.py — attention_split() Replace the "assume 4 GB free" heuristic with `steps = 64`. 64-slice chunking is safe and correct regardless of card size; the 4 GB assumption was fragile on cards with less or more VRAM. 3. diffusionmodules/model.py — slice_attention() Apply the identical `steps = 64` guard to the second call site for the same ZeroDivisionError (was missed in the previous commit). Fixes: github.com/comfyanonymous/ComfyUI/issues/1518 Tested end-to-end on AMD RX 5600 XT (6 GB VRAM), Windows 11, torch-directml 0.2.5, ComfyUI 0.21.1, DreamShaper 8 (SD 1.5). Full 20-step txt2img pipeline completes and returns a valid PNG. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-05-14 21:09:35 -04:00
Emiliooooo	93510fde17	fix(directml): guard opaque tensor storage and zero VRAM edge cases ... Two runtime crashes affect AMD GPU users on Windows using torch-directml: 1. NotImplementedError in module_mmap_residency / cast_to_gathered DirectML tensors are opaque (OpaqueTensorImpl) and do not support untyped_storage(). Wrap both call sites in try/except so mmap tracking is skipped for DirectML tensors instead of crashing. 2. ZeroDivisionError in attention_split DirectML does not expose free VRAM via the standard query path, leaving mem_free_total as 0. Guard the math.log() call with a floor of 4 GB so split-attention steps are computed safely. Tested on AMD RX 5600 XT (6 GB VRAM), Windows 11, torch-directml 0.2.5, ComfyUI 0.21.1, DreamShaper 8 (SD 1.5). Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-05-14 19:20:09 -04:00
Christian Byrne	b112f68681	Generalize frontend version warning to all comfy* requirements.txt entries (#13875)	2026-05-14 16:13:30 -07:00
comfyanonymous	ed78da062c	Create SECURITY.md. (#13902)	2026-05-14 16:02:22 -07:00
comfyanonymous	616cab4f97	Revert "Include workflow_id in all execution WebSocket messages (CORE-198) (#…" (#13901) ... This reverts commit 4f6018982d.	2026-05-14 15:35:42 -07:00
Christian Byrne	4f6018982d	Include workflow_id in all execution WebSocket messages (CORE-198) (#13684)	2026-05-14 15:11:34 -07:00
comfyanonymous	7a063e83a7	Remove annoying message. (#13899)	2026-05-14 12:26:13 -07:00
Robin Huang	3f9bdc70ee	Add careers link to README and startup log (#13897)	2026-05-15 01:32:40 +08:00
Daxiong (Lin)	3d870ff51f	chore: update workflow templates to v0.9.77 (#13895)	2026-05-15 01:25:18 +08:00
Emiliooooo	e860732dba	fix(directml): correct VRAM detection and make torchaudio imports optional ... ## VRAM Detection (model_management.py) The DirectML code path had two hardcoded `1024 * 1024 * 1024 #TODO` values in `get_total_memory()` and `get_free_memory()`, causing ComfyUI to report only 1 GB of VRAM on any AMD/Intel GPU using the DirectML backend — regardless of actual hardware. This forced NORMAL_VRAM or LOW_VRAM calculations to be wildly wrong. Fix for `get_total_memory`: - On Windows, reads `HardwareInformation.qwMemorySize` from the GPU driver registry key via `winreg`. This is the 64-bit accurate value (unlike `Win32_VideoController.AdapterRAM` which overflows at 4 GB). - Allows override via `COMFYUI_DIRECTML_VRAM_MB` env var. - Falls back to 6 GB if registry query fails (safe default for modern dGPUs). Fix for `get_free_memory`: - Uses `torch_directml.gpu_memory(0)` to get per-tile usage fractions and derives free memory as `total * (1 - max_usage_fraction)`. ## torchaudio: optional import on AMD/DirectML torchaudio has a DLL incompatibility with torch-directml (which ships its own torch runtime). The following files had bare `import torchaudio` at module level, crashing ComfyUI startup entirely when torchaudio was absent: - comfy/ldm/lightricks/vae/audio_vae.py - comfy/audio_encoders/whisper.py - comfy/audio_encoders/audio_encoders.py - comfy_extras/nodes_audio.py - comfy_extras/nodes_lt.py - comfy_extras/nodes_wandancer.py Each import is wrapped in `try/except (ImportError, OSError): torchaudio = None`, matching the pattern already used in comfy/ldm/mmaudio/vae/autoencoder.py and comfy/ldm/ace/vae/music_dcae_pipeline.py. Audio nodes will degrade gracefully rather than preventing ComfyUI from starting. Tested on: AMD Radeon RX 5600 XT (6 GB VRAM, gfx1010, Windows 10) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-14 12:10:31 -04:00
Jukka Seppänen	1f28908d6e	Make audio processing nodes handle None -inputs (#13879)	2026-05-14 10:51:35 +08:00
Talmaj	fb51a988b6	Add test that each model has unique identifiers CORE-134 (#13654)	2026-05-14 10:41:25 +08:00
comfyanonymous	26515acd23	ComfyUI v0.21.1	2026-05-13 16:25:01 -04:00
Talmaj	74c17a25e5	Fix void failing with RuntimeError: start (0) + length (464) exceeds dimension size (461). (#13873)	2026-05-13 12:37:30 -07:00
Daxiong (Lin)	afb4fa15d5	chore: update workflow templates to v0.9.75 (#13877) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-05-13 12:33:12 -07:00
Alexander Piskun	b94941d8d3	[Partner Nodes] add Claude LLM node (#13867) ... * [Partner Nodes] add Claude LLM node Signed-off-by: bigcat88 <bigcat88@icloud.com> * [Partner Nodes] add seed param Signed-off-by: bigcat88 <bigcat88@icloud.com> * [Partner Nodes] use image urls instead of base64 Signed-off-by: bigcat88 <bigcat88@icloud.com> * [Partner Nodes] fixed pricing for the claude 4.7 Signed-off-by: bigcat88 <bigcat88@icloud.com> --------- Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-05-13 12:24:58 -07:00
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
Daxiong (Lin)	240363f11e	chore: update embedded docs to v0.5.0 (#13865)	2026-05-13 13:33:29 +08:00
comfyanonymous	2bd65f2091	Better Hidream O1 mem usage factor for non dynamic vram. (#13864)	2026-05-12 20:55:38 -07:00
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
Matt Miller	a5f7bc5658	Suppress false-positive Spectral lint on WebSocket endpoint (#13842) ... The /ws path uses HTTP 101 (Switching Protocols), which is the correct response for a WebSocket upgrade but not a 2xx. The built-in operation-success-response rule fires as a false positive because OpenAPI 3.x has no native WebSocket support. Add a path-scoped override in .spectral.yaml to disable the rule for /ws only, leaving it active for all other operations.	2026-05-12 13:14:50 -07:00
Matt Miller	fb097bedc2	Mark deprecated cloud-runtime endpoints in spec (#13789) ... * Mark deprecated cloud-runtime endpoints in openapi.yaml Add five cloud-runtime FE-facing endpoints to the OSS spec with deprecated: true and standardized description prefixes: - GET /api/history_v2 — superseded by GET /api/jobs - GET /api/history_v2/{prompt_id} — superseded by GET /api/jobs/{prompt_id} - GET /api/logs — returns static placeholder; no real log data - GET /api/viewvideo — alias of GET /api/view for legacy video playback - GET /api/job/{job_id}/status — superseded by GET /api/jobs/{job_id} Each endpoint is tagged x-runtime: [cloud] and follows the same deprecation convention established for /api/history endpoints. Co-authored-by: Matt Miller <MillerMedia@users.noreply.github.com> * fix(spec): consolidate duplicate path entries on deprecated cloud-runtime endpoints Previous commit added new path entries with `deprecated: true` for `/api/job/{job_id}/status`, `/api/history_v2`, `/api/history_v2/{prompt_id}`, `/api/logs`, and `/api/viewvideo`, but the canonical entries already existed elsewhere in the file. Result: 5 duplicate path keys (Spectral parser errors), and the deprecation flag did not land on the operations that FE clients consume by operationId. This commit moves `deprecated: true` plus the standardized "Deprecated." description onto the canonical operations (`getCloudJobStatus`, `getHistoryV2`, `getHistoryV2ByPromptId`, `getCloudLogs`, `viewVideo`) and removes the duplicate entries. Operation IDs and response schemas are unchanged. Spectral lint passes with zero new warnings.	2026-05-12 11:06:28 -07:00
Alexander Piskun	c9589f29b2	[Partner Nodes] fix Quiver nodes (#13851) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-05-12 01:40:15 -07:00
comfyanonymous	0155ddcbe3	Fix dtype issue with hidream o1 (#13849)	2026-05-11 20:53:13 -07:00
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
comfyanonymous	0a7d2ffd68	Support anima TE lora kohya format. (#13847)	2026-05-11 20:01:52 -07:00
rattus	20e439419c	model_patcher: Fix safetensors saving of fp8 (#13835) ... This was missing proper weight scale casting in the saving path.	2026-05-11 12:48:10 -07:00
Alexander Piskun	428c323780	[Partner Nodes] new OpenAI Image node with DynamicCombo and Autogrow (#13838)	2026-05-11 06:19:35 -07:00
Alexander Piskun	46063aa927	[Partner Nodes] new ByteDanceSeedreamNodeV2 node with DynamicCombo and autogrow (#13811) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-05-11 02:53:00 -07:00
Alexander Piskun	b565dc7a6c	[Partner Nodes] new Flux2ImageNode and GrokImageEditNodeV2 nodes with DynamicCombo and Autogrow (#13814)	2026-05-11 01:37:15 -07:00
comfyanonymous	52976f3ea3	ComfyUI v0.21.0	2026-05-10 23:32:00 -04:00
box4wangjing	f505cb4070	chore: remove extra word in comment (#13826)	2026-05-11 11:05:09 +08:00
Daxiong (Lin)	dabfe73dc0	Add New Blueprints (#13570) ... * Add new blueprints * Add Image Segmentation * Add blueprint Get Video Last Frame (#13613) * Add Video segment * Fix Video Stitch subgraph issue * Update get last frame to get any frame * Add Frame Interpolate blueprint * Correct typo * Name blueprints * Update and add new blueprints * blueprints: add subgraph descriptions for previously undocumented workflows Fill missing definitions.subgraphs[].description across ERNIE, Flux.2, Z-Image base/default, Qwen edit 2509, Wan I2V, SAM3 image/video, and align wording with existing blueprint style. * Add new blueprint * remove Image to Video * Update ZIB blueprint * Refine description * Remove duplicate model entries from Image Edit blueprint * Fix typos * Update IDs	2026-05-10 13:50:41 -07:00
Daxiong (Lin)	1eeaf23f20	Remove advanced flag from layers input in EmptyQwenImageLayeredLatentImage node (#13823)	2026-05-11 01:23:04 +08:00