RomanNum3ral
/
ComfyUI
mirror of https://github.com/Comfy-Org/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
5,438 Commits 358 Branches 176 Tags 1.9 GiB
Commit Graph

5438 Commits

Author SHA1 Message Date
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
John Pollock 233f234316 clarify: issue 86 latent-to-pixel resolution mapping 2026-04-19 19:20:14 -05:00
John Pollock 432493c19c fix: issue 86 1024 conditioning gate 2026-04-19 18:23:17 -05:00
Abdul Rehman 138571da95
fix: append directory type annotation to internal files endpoint response (#13078) (#13305) 2026-04-18 23:21:22 -04:00
comfyanonymous 3d816db07f
Some optimizations to make Ernie inference a bit faster. (#13472) 2026-04-18 23:02:29 -04:00
Jukka Seppänen b9dedea57d
feat: SUPIR model support (CORE-17) (#13250) 2026-04-18 23:02:01 -04:00
comfyanonymous 3086026401 ComfyUI v0.19.3 2026-04-17 13:35:01 -04:00
Alexander Piskun 9635c2ec9b
fix(api-nodes): make "obj" output optional in Hunyuan3D Text and Image to 3D (#13449) 
Signed-off-by: bigcat88 <bigcat88@icloud.com>
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
 2026-04-18 01:31:37 +08:00
Daxiong (Lin) f8d92cf313
chore: update workflow templates to v0.9.57 (#13455) 2026-04-17 12:16:39 -05:00
Alexander Piskun 4f48be4138
feat(api-nodes): add new "arrow-1.1" and "arrow-1.1-max" SVG models (#13447) 
Signed-off-by: bigcat88 <bigcat88@icloud.com>
 2026-04-17 12:02:06 -05:00
Alexander Piskun 541fd10bbe
fix(api-nodes): corrected StabilityAI price badges (#13454) 
Signed-off-by: bigcat88 <bigcat88@icloud.com>
 2026-04-17 11:44:08 -05:00
rattus 05f7531148
nodes_textgen: Implement use_default_template for LTX (#13451) 2026-04-17 12:20:09 -04:00
comfyanonymous c033bbf516 ComfyUI v0.19.2 2026-04-17 00:26:35 -04:00
comfyanonymous 1391579c33
Add JsonExtractString node. (#13435) 2026-04-17 00:20:16 -04:00
Alexander Piskun d0c53c50c2
feat(api-nodes): add 1080p resolution for SeeDance 2.0 model (#13437) 
Signed-off-by: bigcat88 <bigcat88@icloud.com>
 2026-04-16 20:32:04 -05:00
Bedovyy b41ab53b6f
Use `ErnieTEModel_` not `ErnieTEModel`. (#13431) 2026-04-16 10:11:58 -04:00
comfyanonymous e9a2d1e4cc
Add a way to disable default template in text gen node. (#13424) 2026-04-15 22:59:08 -04:00
Jun Yamog 1de83f91c3
Fix OOM regression in _apply() for quantized models during inference (#13372) 
Skip unnecessary clone of inference-mode tensors when already inside
torch.inference_mode(), matching the existing guard in set_attr_param.
The unconditional clone introduced in 20561aa9 caused transient VRAM
doubling during model movement for FP8/quantized models.
 2026-04-15 02:10:36 -07:00
comfyanonymous 8f374716ee ComfyUI v0.19.1 2026-04-14 22:56:13 -04:00
comfyanonymous cb0bbde402
Fix ernie on devices that don't support fp64. (#13414) 2026-04-14 22:54:47 -04:00
Daxiong (Lin) 7ce3f64c78
Update workflow templates to v0.9.54 (#13412) 2026-04-14 17:35:27 -07:00
comfyanonymous c5569e8627
Add string output to preview text node. (#13406) 2026-04-14 14:42:23 -04:00
Comfy Org PR Bot c16db7fd69
Bump comfyui-frontend-package to 1.42.11 (#13398) 2026-04-14 14:13:35 -04:00
Daxiong (Lin) fed4ac031a
chore: update workflow templates to v0.9.50 (#13399) 2026-04-14 14:24:37 +08:00
Alexander Piskun 35dfcbbb28
[Partner Nodes] add Sonilo Audio nodes (#13391) 
* feat(api-nodes): add Sonilo nodes

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

* fix: do not spam frontend with each chunk arrival

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

* updated pricing badge

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

---------

Signed-off-by: bigcat88 <bigcat88@icloud.com>
 2026-04-13 22:21:01 -07:00
comfyanonymous 722bc73319
Make text generation work with ministral model. (#13395) 
Needs template before it works properly.
 2026-04-13 20:43:57 -04:00
comfyanonymous 402ff1cdb7
Fix issue with ernie image. (#13393) 2026-04-13 16:38:42 -04:00
comfyanonymous acd718598e ComfyUI v0.19.0 2026-04-13 03:02:36 -04:00
Daxiong (Lin) 559501e4b8
chore: update workflow templates to v0.9.47 (#13385) 2026-04-12 23:19:09 -07:00
Alexander Piskun ee2db7488d
feat(api-nodes): add SeeDance 2.0 nodes (#13364) 
Signed-off-by: bigcat88 <bigcat88@icloud.com>
 2026-04-12 19:26:19 -10:00
comfyanonymous c2657d5fb9
Fix typo. (#13382) 2026-04-12 23:37:13 -04:00