Commit Graph

5913 Commits

Author SHA1 Message Date
comfyanonymous 0eb098b591 Lower peak trellis workflow vram and ram usage. (#16054) 2026-09-03 19:01:51 -04:00
Alexis Rolland 9c90340bc2 Update nodes to improve search rank (#16074) 2026-09-03 15:05:40 -07:00
Jinyan Ye d22a13c667 Support MiniMax-H3 and HiDream O1 loras trained with DiffSynth-Studio / ModelScope (#15662) 2026-09-03 14:05:26 -07:00
Jukka Seppänen 1aec3a1351 MiniMax-H3: Make VAE optional, allow using text encoder only references (#16065) 2026-09-03 15:51:47 -04:00
Alexis Rolland 5f056310d5 Update README.md (#16071)
ComfyUI Desktop has proven to be the easiest way to install and manage local ComfyUI instances. We will still maintain a portable version for now but this change is to nudge the community in using Desktop instead.
2026-09-03 12:36:25 -07:00
Maanil Verma 30bdda1ef1 Register partner_run_gate_enabled feature flag (#16012)
The frontend's partner-nodes run gate (Comfy-Org/ComfyUI_frontend#15248)
reads this key from /features as its kill switch. Registering it makes
--feature-flag partner_run_gate_enabled=false coerce to a real boolean;
unregistered keys pass through as strings, and the string "false" is
truthy to the frontend, so the switch would silently not work.
2026-09-03 17:45:08 +05:30
comfyanonymous 345c919049 Add warning about forcing single GPU mode on Windows (#16055) 2026-09-02 22:48:06 -04:00
Terry Jia 1af040bf02 Emit the document canvas from ImageCompositor for the layer editor (#15742) 2026-09-02 18:57:55 -07:00
Terry Jia 5672751416 Add live resolution preview widget to ResolutionSelector (#16013) 2026-09-02 15:29:16 -07:00
Tijana Vukovic 13d2580501 Enable PyTorch SDPA attention and FP8 ops for gfx1171 (#16039) 2026-09-02 18:13:17 -04:00
ussoewwin 2035799189 Fix SAM3 segmentation head receiving 4 FPN levels when scalp=1 (#15979) 2026-09-02 14:47:17 -07:00
Daxiong (Lin) a87667f72f chore: update workflow templates to v0.11.54 (#16045) 2026-09-02 10:46:37 -07:00
Alexander Piskun ec803fc97e [Partner Nodes] feat(Minimax-H3): add the Max model to the Reference node (#16041)
* [Partner Nodes] feat(MiniMax): add H3 Max option to H3 reference-to-video node

Signed-off-by: Alexander Piskun <bigcat88@icloud.com>
2026-09-02 19:29:30 +04:00
Terry Jia ace9172e95 Annotate temp paths in Preview3DAdvanced / PreviewGaussianSplat / PreviewPointCloud outputs (#16038) 2026-09-02 07:35:27 -04:00
comfyanonymous 4e024cb1e8 Lower trellis workflow remesh memory usage. (#16034) 2026-09-01 22:43:25 -04:00
Daxiong (Lin) 03468f4e3e chore: update workflow templates to v0.11.52 (#16024)
Co-authored-by: Purz <97489706+purzbeats@users.noreply.github.com>
2026-09-01 21:02:12 -04:00
Purz 624f56565b [Partner Nodes] feat(MiniMax): add H3 Max option to H3 text-to-video and first-last-frame nodes (#16025)
* [Partner Nodes] feat(MiniMax): add H3 Max option to H3 text-to-video and first-last-frame nodes

Signed-off-by: Alexander Piskun <bigcat88@icloud.com>

* [Partner Nodes] fix(downscale): never make a downscaled image more elongated than its source

Signed-off-by: Alexander Piskun <bigcat88@icloud.com>

* [Partner Nodes] fix(M3-Max): add check fpr max prompt length

Signed-off-by: Alexander Piskun <bigcat88@icloud.com>

* [Partner Nodes] chore(Minimax): correct route name

Signed-off-by: bigcat88 <bigcat88@icloud.com>

---------

Signed-off-by: Alexander Piskun <bigcat88@icloud.com>
Signed-off-by: bigcat88 <bigcat88@icloud.com>
Co-authored-by: Alexander Piskun <13381981+bigcat88@users.noreply.github.com>
Co-authored-by: Alexander Piskun <bigcat88@icloud.com>
2026-09-01 20:58:21 -04:00
Tijana Vukovic cf7aedc1e6 Enable PyTorch SDPA attention and FP8 ops for gfx1170 (#16014) 2026-09-01 20:20:43 -04:00
comfyanonymous 3258eb3a4d Disable ck attention when fp32 + low_precision_attention False. (#16029) 2026-09-01 19:59:29 -04:00
Jukka Seppänen 02aa70781a Allow using references with MiniMax-H3 Fun Union and fix prefetch race condition (#16020) 2026-09-01 19:09:42 -04:00
T8star-Aix 3216c62e99 Support SenseNova U1.5 (CORE-411) (#15922) 2026-08-31 20:05:53 -07:00
comfyanonymous d3eaf6adb3 Minimax h3 controlnet as a model patch instead of a controlnet. (#15975) 2026-08-31 19:44:42 -04:00
comfyanonymous a8b4fa6410 Add how to cache model stuff to AGENTS.md (#16003) 2026-08-31 19:09:43 -04:00
comfyanonymous 95d755cd81 Disable push event trigger for failing workflow. (#15995) 2026-08-30 23:19:14 -04:00
Terry Jia f938505952 feat: add VideoTrim and VideoCrop nodes with VIDEO_EDIT widget inputs (#15637) 2026-08-30 15:54:48 -07:00
comfyanonymous 8a33128f2f Improve some warning messages. (#15977) 2026-08-29 20:10:20 -04:00
Alexander Piskun 5bdcb5f4ed [Partner Nodes] fix(HeyGen): update Avatar Video price badge (#15945)
Signed-off-by: bigcat88 <bigcat88@icloud.com>
2026-08-29 21:53:58 +04:00
comfyanonymous e7051b0375 Add section about user input tolerance to AGENTS.md (#15955) 2026-08-28 20:00:29 -04:00
Jukka Seppänen 2504e68d4d MiniMax-H3: Support PDD LoRA (#15908) 2026-08-28 18:12:36 -04:00
comfyanonymous 3ac5d7941d Add cfgpp_ud10_ab sampler. (#15951)
This is the result of an experiment where I asked a LLM to create a better
sampler for the base Anima model and gave it a lot of different things to
try.

I wouldn't call this revolutionary but from my basic testing it seems to be
a bit better than the other samplers at lower steps so I have decided to
include it in ComfyUI.

For best result use it at CFG 2.0 on base Anima. It should also work on
other models but I'm not sure about the optimal parameters.
2026-08-28 15:33:18 -04:00
comfyanonymous 0a33ed6c28 Add to readme that we support HDR and high bit depth. (#15940) 2026-08-27 22:57:30 -04:00
Terry Jia a255b96872 feat(3d): File3DToMesh node — parse GLB/GLTF/OBJ/STL into MESH (#15919) 2026-08-27 18:35:30 -07:00
Alexander Piskun 4c6359f2e3 [Partner Nodes] feat(Google-Omni): add support for Omni 1.1 model (#15929)
Signed-off-by: Alexander Piskun <bigcat88@icloud.com>
Co-authored-by: Purz <97489706+purzbeats@users.noreply.github.com>
2026-08-27 18:29:35 -04:00
Daxiong (Lin) e20d433a49 chore: update workflow templates to v0.11.50 (#15931) 2026-08-27 12:21:54 -07:00
Alexander Piskun 77739723a3 fix(memory): respect the container cgroup memory limit instead of host RAM (#15927) 2026-08-27 07:57:31 -07:00
Alexander Piskun d8e7bbc9d5 fix(video): remux HEVC to mp4/mov as hvc1 via hevc_mp4toannexb (#15809) 2026-08-26 20:28:50 -04:00
comfyanonymous 5653b4ac8e Support avif in Save Image Advanced node. (#15891) 2026-08-26 19:17:57 -04:00
Comfy Org PR Bot 40b9898582 Bump comfyui-frontend-package to 1.51.9 (#15696) 2026-08-26 16:05:39 -07:00
Alexander Piskun a25c7bf2b8 [Partner Nodes] feat(WAN): add WAN3-Prime model support (#15894)
Signed-off-by: Alexander Piskun <bigcat88@icloud.com>
2026-08-26 22:26:03 +04:00
Alexander Piskun 30d03fea0a [Partner Nodes] feat(Recraft): add V4 Styles (#15903)
Signed-off-by: Alexander Piskun <bigcat88@icloud.com>
2026-08-26 22:22:22 +04:00
Alexander Piskun b133e48368 [Partner Nodes] chore(Google): drop retiring Veo 2 and Veo 3.0 models (#15883)
Signed-off-by: Alexander Piskun <bigcat88@icloud.com>
2026-08-26 12:30:06 +04:00
comfyanonymous 12d5279438 ComfyUI v0.34.0 v0.34.0 2026-08-25 17:58:26 -04:00
Daxiong (Lin) ef0d752e5e Update workflow templates to v0.11.48 (#15888) 2026-08-25 13:29:16 -07:00
Alexander Piskun 7d9d0c391b [Partner Nodes] feat(Pixverse): add Pixverse V6 model support (#15880)
Signed-off-by: Alexander Piskun <bigcat88@icloud.com>
2026-08-25 23:40:46 +04:00
rattus 7a054eb472 comfy-aimdo 0.4.15 (#15886)
Comfy-aimdo 0.4.15 fixes the headroom on the NVML pressure mechanism.
Some system have only NVML as the pressure out and this could cause
shared VRAM spills. This bumps the headroom to 512MB.

I never reproduced this issue.
2026-08-25 12:12:40 -04:00
Alexander Piskun a1079ba16f [Partner Nodes] chore(Tripo): remove retired Refine node and v2.0 model version (#15851)
Signed-off-by: bigcat88 <bigcat88@icloud.com>
2026-08-25 10:25:23 +04:00
comfyanonymous 2618d32dfb Python 3.10 will be EOL soon, please upgrade. (#15874)
After the Python 3.10 EOL date of October 31 2026 we will put zero effort into keeping support for python 3.10 so everyone is recommended to upgrade to a newer version.
2026-08-24 23:09:38 -04:00
Constantine 5f0c4e18cb Fix default database path for custom user directory (#14539)
* fix: respect user directory for default database

* refactor: use None default for --database-url instead of argv scan

Per review: default --database-url to None and treat a non-None value
as explicit at resolution time. Removes the sys.argv scan and the
database_url_explicit attribute. database_default_path now serves
directly as the legacy copy source. Adds regression tests for the
unchanged no-flag default path and explicit URLs at the legacy
location.

* refactor: rename legacy database to .bak after copy

Per review: after copying the legacy install-dir database to the
effective user directory, rename the original to comfyui.db.bak so a
later launch without --user-directory cannot silently fall back to a
diverged copy, while keeping the file around for recovery. Also hoist
the database_default_path import to module scope.

* fix: guard legacy migration on existing .bak and rename before copy

Per review: bail out of the legacy migration when comfyui.db.bak
already exists, so only the first run migrates and later launches with
a fresh --user-directory cannot grab a database another instance is
using. Rename before copy so os.replace fails fast if the legacy DB is
held open by a running instance.

---------

Co-authored-by: guill <jacob.e.segal@gmail.com>
2026-08-24 16:19:03 -07:00
Alexis Rolland eb8cad7375 Update nodes_image_compare.py (#15868) 2026-08-24 16:56:59 -04:00
Daxiong (Lin) 180060c295 chore: update workflow templates to v0.11.46 (#15864) 2026-08-24 11:31:42 -07:00