5254 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
rattus	d214aaf21e	Merge ea5775c620 into 77e2ed5e01	2026-05-15 03:23:20 +00:00
rattus	ea5775c620	Merge pull request #9 from rattus128/dev/threaded-loader-2-ram-cache ... threaded loader 2 + ram cache (CORE-43,CORE-117)	2026-05-15 13:23:16 +10:00
Rattus	55197d8bfc	bump aimdo	2026-05-15 13:19:57 +10:00
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
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
Rattus	d8b442709a	make default	2026-05-15 00:37:06 +10:00
Rattus	18a74cb96a	cli_args/execution: Implement lower background cache-ram threshold ... Limit the amount of RAM background intermediates can use, so that switching workflows doesn't degrade performance too much.	2026-05-15 00:36:35 +10:00
Rattus	31150538b0	implement pin registration swaps ... Uncap the windows pins from 50% by extending the pool and have a pressure mechanism to move the pin reservations om demand. This unfortunately implies a GPU sync to do the freeing so significant hysterisis needs to be added to consolidate these pressure events.	2026-05-15 00:35:23 +10:00
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
Rattus	3f717816e1	execution: implement pin eviction on RAM presure ... Add back proper pin freeing on RAM pressure	2026-05-13 22:23:54 +10:00
Rattus	d61026d020	pins: implement freeing intermediate for pinned memory ... Pinning is more important than inactive intermediates and the stream pin buffer is more important than even active intermediates.	2026-05-13 22:23:54 +10:00
Rattus	ee927aafa8	ops: sync the CPU with only the offload stream activity ... This was syncing with the offload stream which itself is synced with the compute stream, so this was syncing CPU with compute transitively. Define the event to sync it more gently.	2026-05-13 22:23:54 +10:00
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	44c0a0602b	ops: remove unused arg ... This was defeatured in aimdo iteration	2026-05-12 11:04:59 +10:00
Rattus	c395f2d5b7	requirements: comfy-aimdo 0.4.0	2026-05-12 11:04:59 +10:00
Rattus	3a3b75a7e3	implement pinned loras	2026-05-12 11:04:59 +10:00
Rattus	e48dace145	prepare for multiple pin sets	2026-05-12 11:04:59 +10:00
Rattus	8e473d756f	lora: re-implement as inplace swiss-army-knife operation	2026-05-12 11:04:59 +10:00
Rattus	2b927e1783	LowVRAMPatch: change to two-phase visit	2026-05-12 11:04:59 +10:00
Rattus	8187cd783e	Implement JIT pinned memory pressure ... Replace the predictive pin pressure mechanism with JIT PIN memory pressure.	2026-05-12 11:04:59 +10:00
Rattus	17955235b2	remove old pin path	2026-05-12 11:04:59 +10:00
Rattus	8070cb7780	Add stream host pin buffer for AIMDO casts ... Introduce per-offload-stream HostBuffer reuse for pinned staging, include it in cast buffer reset synchronization. Defer actual casts that go via this pin path to a separate pass such that the buffer can be allocated monolithically (to avoid cudaHostRegister thrash).	2026-05-12 11:04:59 +10:00
Rattus	b66b642068	mm: use aimdo to do transfer from disk to pin ... Aimdo implements a faster threaded loader.	2026-05-12 11:04:59 +10:00
Rattus	157965a1c9	pinned_memory: implement with aimdo growable buffer ... Use a single growable buffer so we can do threaded pre-warming on pinned memory.	2026-05-12 11:04:59 +10:00
Rattus	1fe3a13f84	model_management: disable non-dynamic smart memory ... Disable smart memory outright for non dynamic models. This is a minor step towards deprecation of --disable-dynamic-vram and the legacy ModelPatcher. This is needed for estimate-free model development, where new models can opt-out of supplying a memory estimate and not have to worry about hard VRAM allocations due to legacy non-dynamic model patchers This is also a general stability increase for a lot of stray use cases where estimates may still be off and going forward we are not going to accurately maintain such estimates.	2026-05-12 11:04:59 +10:00
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