RomanNum3ral
/
ComfyUI
mirror of https://github.com/Comfy-Org/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
5,179 Commits 309 Branches 168 Tags 1.9 GiB
Commit Graph

5179 Commits

Author SHA1 Message Date
Jedrzej Kosinski b502bcfff9 Merge remote-tracking branch 'origin/master' into worksplit-multigpu 2026-04-20 02:38:33 -07:00
Jedrzej Kosinski 37deccb0d4
Fix Hunyuan 3D 2.1 multi-GPU worksplit: use cond_or_uncond instead of hardcoded chunk(2) (#13478) 2026-04-20 02:37:18 -07:00
comfyanonymous fc5f4a996b
Add link to Intel portable to Readme. (#13477) 2026-04-19 20:26:12 -04:00
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
rattus f0d550bd02
Minor updates for worksplit_gpu with comfy-aimdo (#13419) 
* main: init all visible cuda devices in aimdo

* mp: call vbars_analyze for the GPU in question

* requirements: bump aimdo to pre-release version
 2026-04-15 22:49:01 -07:00
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
comfyanonymous 971932346a
Update quant doc so it's not completely wrong. (#13381) 
There is still more that needs to be fixed.
 2026-04-12 23:27:38 -04:00
comfyanonymous 31283d2892
Implement Ernie Image model. (#13369) 2026-04-11 22:29:31 -04:00
comfyanonymous 55ebd287ee
Add a supports_fp64 function. (#13368) 2026-04-11 21:06:36 -04:00
comfyanonymous a2840e7552
Make ImageUpscaleWithModel node work with intermediate device and dtype. (#13357) 2026-04-10 21:48:26 -04:00
Jukka Seppänen a134423890
SDPose: resize input always (#13349) 2026-04-10 11:26:55 -10:00
Daxiong (Lin) b920bdd77d
chore: update workflow templates to v0.9.45 (#13353) 2026-04-10 15:50:40 -04:00
Alexander Piskun 5410ed34f5
fix(api-nodes): fix GrokVideoReferenceNode price badge (#13354) 2026-04-10 08:01:15 -10:00
Terry Jia e6be419a30
should use 0 as defalut for brightness (#13345) 2026-04-09 21:58:05 -04:00
comfyanonymous 3d4aca8084
Bump comfyui-frontend-package version to 1.42.10 (#13346) 2026-04-09 21:56:49 -04:00
Jedrzej Kosinski 48deb15c0e
Simplify multigpu dispatch: run all devices on pool threads (#13340) 
Benchmarked hybrid (main thread + pool) vs all-pool on 2x RTX 4090
with SD1.5 and NetaYume models. No meaningful performance difference
(within noise). All-pool is simpler: eliminates the main_device
special case, main_batch_tuple deferred execution, and the 3-way
branch in the dispatch loop.
 2026-04-09 01:15:57 -07:00
comfyanonymous 2d861fb146
Basic intel standalone package .bat (#13333) 2026-04-08 21:39:29 -04:00
Jedrzej Kosinski 4b93c4360f
Implement persistent thread pool for multi-GPU CFG splitting (#13329) 
Replace per-step thread create/destroy in _calc_cond_batch_multigpu with a
persistent MultiGPUThreadPool. Each worker thread calls torch.cuda.set_device()
once at startup, preserving compiled kernel caches across diffusion steps.

- Add MultiGPUThreadPool class in comfy/multigpu.py
- Create pool in CFGGuider.outer_sample(), shut down in finally block
- Main thread handles its own device batch directly for zero overhead
- Falls back to sequential execution if no pool is available
 2026-04-08 05:39:07 -07:00
Jedrzej Kosinski da3864436c Merge remote-tracking branch 'origin/master' into worksplit-multigpu 2026-04-08 05:08:38 -07:00
huemin b615af1c65
Add support for small flux.2 decoder (#13314) 2026-04-07 03:44:18 -04:00
comfyanonymous 40862c0776
Support Ace Step 1.5 XL model. (#13317) 2026-04-07 03:13:47 -04:00
Terry Jia 50076f3439
format blueprint (#13315) 
Co-authored-by: guill <jacob.e.segal@gmail.com>
 2026-04-06 23:33:55 -04:00
comfyanonymous 61c2387436
Ace step empty latent nodes follow intermediate dtype. (#13313) 2026-04-06 18:12:16 -07:00
Terry Jia 7083484a48
image histogram node (#13153) 
* image histogram node

* update color curve blueprint using image histogram node

---------

Co-authored-by: guill <jacob.e.segal@gmail.com>
 2026-04-06 14:54:02 -07:00