RomanNum3ral
/
ComfyUI
mirror of https://github.com/Comfy-Org/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
5,818 Commits 370 Branches 178 Tags 1.9 GiB
Commit Graph

5818 Commits

Author SHA1 Message Date
Jukka Seppänen db85cf03ff
feat: RIFE and FILM frame interpolation model support (CORE-29) (#13258) 
* initial RIFE support

* Also support FILM

* Better RAM usage, reduce FILM VRAM peak

* Add model folder placeholder

* Fix oom fallback frame loss

* Remove torch.compile for now

* Rename model input

* Shorter input type name

---------
 2026-04-22 04:16:02 -07:00
Matt Miller 91e1f45d80
fix(veo): reject 4K resolution for veo-3.0 models in Veo3VideoGenerationNode (#13504) 
The tooltip on the resolution input states that 4K is not available for
veo-3.1-lite or veo-3.0 models, but the execute guard only rejected the
lite combination. Selecting 4K with veo-3.0-generate-001 or
veo-3.0-fast-generate-001 would fall through and hit the upstream API
with an invalid request.

Broaden the guard to match the documented behavior and update the error
message accordingly.

Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
 2026-04-21 22:31:36 -07:00
Daxiong (Lin) 6045c11d8b
chore: update workflow templates to v0.9.59 (#13507) 2026-04-21 20:45:25 -07:00
comfyanonymous 529c80255f
Allow logging in comfy app files. (#13505) 2026-04-21 22:59:31 -04:00
AustinMroz 43a1263b60
Add gpt-image-2 as version option (#13501) 2026-04-21 17:58:59 -07:00
Comfy Org PR Bot 102773cd2c
Bump comfyui-frontend-package to 1.42.14 (#13493) 2026-04-21 11:35:45 -07:00
Alexander Piskun 1e1d4f1254
[Partner Nodes] added 4K resolution for Veo models; added Veo 3 Lite model (#13330) 
* feat(api nodes): added 4K resolution for Veo models; added Veo 3 Lite model

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

* increase poll_interval from 5 to 9

---------

Signed-off-by: bigcat88 <bigcat88@icloud.com>
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
 2026-04-21 11:27:35 -07:00
Jukka Seppänen eb22225387
Support standalone LTXV audio VAEs (#13499) 2026-04-21 10:46:37 -07:00
Alexander Piskun b38dd0ff23
feat(api-nodes): add automatic downscaling of videos for ByteDance 2 nodes (#13465) 2026-04-21 10:45:10 -07:00
comfyanonymous ad94d47221
Make the ltx audio vae more native. (#13486) 2026-04-21 11:02:42 -04:00
Comfy Org PR Bot e75f775ae8
Bump comfyui-frontend-package to 1.42.12 (#13489) 2026-04-21 00:43:11 -07:00
John Pollock 1e93c08517 Merge pull request #15 from pollockjj/issue_80 
Fix Trellis VAE decode memory management
 2026-04-20 20:24:48 -07:00
John Pollock e8402d94b4 Address Trellis VAE decode review feedback 2026-04-20 22:10:15 -05:00
John Pollock 7e9ee82351 Merge remote-tracking branch 'origin/issue_73' into issue_80 
# Conflicts:
#	comfy_extras/nodes_trellis2.py
 2026-04-20 22:04:24 -05:00
comfyanonymous c514890325
Refactor io to IO in nodes_ace.py (#13485) 2026-04-20 21:59:26 -04:00
John Pollock b896abf836 Merge pull request #14 from pollockjj/issue_88 
Trellis2: fix texture path resolution and gpu-only host conversion
 2026-04-20 18:55:56 -07:00
John Pollock 3546836091 Fix Trellis VAE decode memory management 2026-04-20 20:39:08 -05:00
John Pollock 972f9ca517 Merge remote-tracking branch 'origin/issue_73' into issue_88 2026-04-20 20:00:52 -05:00
John Pollock da6f3b630f Merge pull request #13 from pollockjj/issue_94 
Trellis2: make textured mesh simplification deterministic
 2026-04-20 17:57:01 -07:00
Octopus 543e9fba64
fix: pin SQLAlchemy>=2.0 in requirements.txt (fixes #13036) (#13316) 2026-04-20 15:30:23 -07:00
John Pollock 2db06439ad Merge pull request #12 from pollockjj/issue_87 
Issue 87: fix Trellis2 batch semantics collapse shape and texture samples
 2026-04-20 15:24:35 -07:00
John Pollock de7a811cdd fix: stabilize Trellis2 mesh simplification 2026-04-20 17:22:31 -05:00
John Pollock 0f530ce540 Omit null batch_index from Trellis upsample output 2026-04-20 17:20:57 -05:00
John Pollock 8f3d52fd49 Validate Trellis coord_counts noise metadata 2026-04-20 17:17:50 -05:00
John Pollock 149af779ed Harden Trellis sparse latent seeding 2026-04-20 16:05:10 -05:00
John Pollock 081e7126bd Fail loud on Trellis invalid batch metadata 2026-04-20 15:50:40 -05:00
John Pollock f309cc1889 Harden Trellis sparse metadata validation 2026-04-20 14:46:23 -05:00
John Pollock 73ca4a452e fix: issue 88 make texture voxel query deterministic 2026-04-20 14:44:45 -05:00
John Pollock b1f6eb562c fix: issue 88 unify texture paint color path on host 2026-04-20 14:39:15 -05:00
John Pollock a0e5da14e7 fix: issue 88 texture path resolution and gpu-only host conversion 2026-04-20 14:35:08 -05:00
John Pollock e95be49e69 Fix Trellis seeded sparse batch semantics 2026-04-20 14:29:07 -05:00
John Pollock 032943a065 Fix Trellis PR review regressions 2026-04-20 12:15:49 -05:00
John Pollock eaf7d708b0 Fix Trellis2 batched shape and texture semantics 2026-04-20 11:06:04 -05:00
John Pollock 5ec794f423 Merge pull request #11 from pollockjj/issue_76_extract 
Trellis2/Hunyuan3d: n>1 batched cascade support
 2026-04-19 21:51:27 -07:00
John Pollock e2bbcece02 Trellis2: inline batched mesh helpers 2026-04-19 23:47:57 -05:00
John Pollock 6e45580707 Trellis2: share batched mesh helpers 2026-04-19 23:33:09 -05:00
John Pollock 849a75c4dc Trellis2: handle empty and batched texture paint paths 2026-04-19 23:23:24 -05:00
John Pollock 353f3d9164 Trellis2/Hunyuan3d: preserve mesh tensor contract in batch mode 2026-04-19 22:55:38 -05:00
John Pollock eb3ac5ffe4 Trellis2/Hunyuan3d: n>1 batched cascade support 
Mesh-producing nodes (VoxelToMeshBasic, VoxelToMesh, VaeDecodeShapeTrellis)
previously stacked per-batch vertex/face tensors with torch.stack, which
failed under batch>1 because per-item meshes have variable shapes. Store
per-item tensors as lists when shapes differ; keep stacked-tensor fast
path when shapes match. Update SaveGLB, PostProcessMesh, and
VaeDecodeTextureTrellis consumers to iterate per-item when input is a
list.

Trellis2Conditioning.execute previously collapsed batched image/mask
input to index 0, yielding identical conditioning for every batch item.
Loop over the batch and produce per-image cond_512/cond_1024/neg_cond
tensors stacked along the batch dim, matching the latent batch size.

batch_size=1 behavior is unchanged. batch_size>1 runs now emit one GLB
per batch item per SaveGLB node and carry per-image conditioning
through the structure/shape/texture cascade.
 2026-04-19 22:03:53 -05:00
John Pollock 5d0c6cc7be Merge pull request #10 from pollockjj/issue_74_extract 
Trellis2: fix structure batch pruning under shape_rule
 2026-04-19 19:57:29 -07:00
John Pollock e11bd314be Trellis2: guard structure shape_rule pruning to CFG batches 2026-04-19 21:38:45 -05:00
John Pollock 65430280ff Trellis2: slice cond half of x symmetrically under shape_rule pruning 2026-04-19 21:26:48 -05:00
John Pollock 845932eaef Merge pull request #8 from pollockjj/issue_89 
Restore Trellis2 clip vision image_size state
 2026-04-19 19:17:12 -07:00
John Pollock 3b0adb5ac2 Add Trellis2 image_size restore tests 2026-04-19 21:11:58 -05:00
John Pollock 78d4f27ec0 Match Copilot image_size restore pattern 2026-04-19 21:05:07 -05:00
John Pollock e91a4659d5 Handle missing Trellis2 image_size restore state 2026-04-19 20:51:22 -05:00
John Pollock 1c91682604 Guard full Trellis2 conditioning image_size restore 2026-04-19 20:49:42 -05:00
John Pollock 718be91a15 Restore Trellis2 clip vision image_size state 2026-04-19 19:53:30 -05:00
comfyanonymous fc5f4a996b
Add link to Intel portable to Readme. (#13477) 2026-04-19 20:26:12 -04:00
John Pollock d67432586e Merge pull request #7 from pollockjj/issue_86 
Issue 86: fix Trellis2 1024 conditioning gate
 2026-04-19 17:24:35 -07:00