5607 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
sean-kim05	2eac058daa	Merge 7cd78e02aa into 1d1099bea0	2026-07-17 12:59:40 -07:00
Daxiong (Lin)	1d1099bea0	chore: update workflow templates to v0.11.11 (#14973)	2026-07-18 00:53:15 +08:00
Comfy Org PR Bot	c67f95607f	chore(openapi): sync shared API contract from cloud@4acc59a (#14947)	2026-07-17 18:29:45 +02:00
Alexander Piskun	8edea4a65d	[Partner Nodes] feat(Google): add Gemini 3.5 Flash LLM model (#14972) ... Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>	2026-07-17 19:24:34 +03:00
comfyanonymous	0f42ba5146	Support anima lllite control models. (#14954) ... Put them in the models/model_patches folder. Use the new AnimaLLLiteApply node.	2026-07-17 07:36:21 -07:00
comfyanonymous	71b73e3b2b	Speed up anima a bit. (#14953)	2026-07-16 19:44:02 -07:00
comfyanonymous	6a8ff7a929	Various comfy kitchen optimizations and fixes. (#14963)	2026-07-16 19:43:12 -07:00
Alexander Piskun	285a98944c	[Partner Nodes] feat(OpenAI): add GPT5.6 models (#14957) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-07-16 15:35:07 +03:00
彼彼	03978e1e81	[feat]Add JoyImageEdit native model support (#14428)	2026-07-15 23:48:28 -04:00
comfyanonymous	678d42c90e	Update AGENTS.md (#14955)	2026-07-15 20:09:59 -07:00
Alexis Rolland	87d23b8176	[Partner Nodes] feat(client): send ComfyUI Job Id in request headers (#14934)	2026-07-15 16:38:03 +08:00
Alexander Piskun	cc6b352511	fix(Video): stream the video transcode instead of buffering every frame in RAM (CORE-353) (CORE-351) (#14813)	2026-07-15 15:23:43 +08:00
comfyanonymous	700821e136	ComfyUI v0.28.0	2026-07-15 01:43:14 -04:00
Comfy Org PR Bot	3cd13eb424	Bump comfyui-frontend-package to 1.45.21 (#14944)	2026-07-15 01:29:24 -04:00
Alexander Piskun	1701cce8dc	Fix cached outputs missing from job results when prompt has no client_id (#14939) ... When a prompt is submitted without client_id and its output nodes are served from cache, _send_cached_ui returned early before recording the cached UI outputs, so /api/jobs/{job_id} (and /history) reported success with empty outputs. Record the outputs before the client_id check.	2026-07-14 14:29:01 -07:00
Alexander Piskun	26537080cb	[Partner Nodes] feat(sync.so): add support for "sync-3" model (#14928) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-07-14 23:21:20 +03:00
comfyanonymous	dff0b18fff	Fix int8 performance regression on 16xx series. (#14941)	2026-07-14 13:13:08 -07:00
Sean Kim	7cd78e02aa	Honor strict_duration in VideoFromComponents.as_trimmed	2026-07-13 22:50:12 -07:00
Terry Jia	0aecac867d	Fix 3D advanced nodes crashing in API mode (no UI) (#14930)	2026-07-14 10:07:23 +08:00
comfyanonymous	80acfcf0fe	More optimized int8 and int4 on turing. (#14927)	2026-07-13 13:03:29 -07:00
comfyanonymous	c35a622acd	Fix hidream o1 regression. (#14923)	2026-07-13 12:52:28 -07:00
Daxiong (Lin)	da2608926e	Update workflow templates to v0.11.9 (#14924)	2026-07-13 12:15:34 -07:00
Comfy Org PR Bot	5658a68a87	chore(openapi): sync shared API contract from cloud@bcb8f5f (#14815) ... Co-authored-by: mattmillerai <7741082+mattmillerai@users.noreply.github.com> Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com> Co-authored-by: Matt Miller <mattmiller@comfy.org>	2026-07-13 10:20:58 -07:00
Daxiong (Lin)	5bb831a3f5	chore: update embedded docs to v0.5.8 (#14920)	2026-07-13 22:13:23 +08:00
Alexander Piskun	5697b97017	[Partner Nodes] chore(Google): reroute Gemini Image preview models to release versions (#14917) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-07-13 14:18:09 +03:00
Alexander Piskun	ec0e8b3447	fix(image): support single-channel images in Save Image (Advanced) (#14761) ... Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>	2026-07-13 11:38:50 +03:00
Alexander Piskun	8deaa4d911	fix(image): correct HLG inverse-OETF clamp in hlg_to_linear (#14762) ... Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>	2026-07-13 10:53:37 +03:00
Alexander Piskun	b58f829b57	[Partner Nodes] feat(client): send ComfyUI Core version in request headers (#14910) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-07-13 10:38:35 +03:00
comfyanonymous	917faef771	Support PID 1.5 models. (#14894)	2026-07-12 09:43:30 -07:00
Gustavo Schneiter	8b099de36a	Fix SaveVideo description: says images, saves video (#14885)	2026-07-12 12:58:25 +08:00
comfyanonymous	69ea58697b	Try to fix flash attention related issue on AMD. (#14880)	2026-07-11 17:16:40 -07:00
comfyanonymous	f3a36e7484	Temporarily disable auto enabling triton by default on AMD. (#14878) ... I get freezing issues on my test machine.	2026-07-10 18:37:59 -07:00
comfyanonymous	92ddf07ba1	Try to fix some issues with the seedvr VAE. (#14877)	2026-07-10 19:54:28 -04:00
Alexis Rolland	1f51e146a8	chore: Update preview nodes (#14871)	2026-07-10 19:32:53 -04:00
Alexis Rolland	5976ee37cd	Bringing back the text node (#14870)	2026-07-10 19:31:39 -04:00
Terry Jia	328144ce24	CORE-329 feat: add Save 3D (Advanced) node family (#14701)	2026-07-11 04:03:34 +08:00
Terry Jia	8310b0e0db	feat: add bboxes input to Create Bounding Boxes node (#14724)	2026-07-11 03:58:03 +08:00
Yousef R. Gamaleldin	94fa08223e	Save Text Node (CORE-176) (#14102)	2026-07-11 03:54:56 +08:00
liminfei-amd	1377a2f729	Only auto-enable the ROCm comfy-kitchen Triton backend on matrix-core GPUs (#14869) ... #14862 auto-enables the comfy-kitchen Triton backend whenever torch.version.hip is set and Triton >= 3.7. The INT8 matmul kernels compile tl.dot to matrix-core instructions (WMMA on RDNA3+/gfx11xx-gfx12xx, MFMA on CDNA/gfx9xx); RDNA1/RDNA2 (gfx10xx) have neither, so the auto-enabled INT8 path hangs the GPU there (reported on RDNA2 + triton-windows 3.7.1: native and custom-node INT8 freeze until reset). Gate the automatic ROCm default on GPU architecture as well as Triton version so RDNA1/RDNA2 stay on the working eager fallback. Add --disable-triton-backend as an explicit override; --enable-triton-backend still force-enables on any arch.	2026-07-10 03:31:20 -07:00
Alexander Piskun	206b9245dc	[Partner Nodes] fix(Tencent): restore Tencent3DPartNode FBX output via staged generation (#14867) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-07-10 12:33:32 +03:00
Alexander Piskun	89ecc5cf8c	[Partner Nodes] feat(Seedream): add widget to disable thinking (#14853) ... Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Daxiong (Lin) <contact@comfyui-wiki.com>	2026-07-10 11:58:22 +03:00
John Pollock	8e2e54e2b8	Add SeedVR2 support (CORE-6) (#14424)	2026-07-10 15:07:42 +08:00
comfyanonymous	e2a6e30d89	Fix black image on turing when using int4 models. (#14864)	2026-07-09 23:17:06 -04:00
liminfei-amd	099522f85b	Enable comfy-kitchen Triton backend by default on ROCm/AMD (#14862) ... On AMD/ROCm the CUDA backend is unavailable, so Triton is the only accelerated comfy-kitchen backend. It was disabled by default (opt-in --enable-triton-backend), leaving AMD on the slow eager path. Enable it by default when torch.version.hip is set AND Triton is >= 3.7 -- older Triton lacks libdevice.rint on the HIP backend and hard-crashes the INT8 path, so on Triton < 3.7 it stays disabled with a log line. NVIDIA behavior is unchanged; the explicit --enable-triton-backend flag still works as an override. Fixes #14861	2026-07-09 23:11:52 -04:00
liminfei-amd	62e025a4f3	Fix FP8 activation quantization for >2D activations in mixed_precision_ops (#14643) ... mixed_precision_ops.Linear.forward only quantized activations that were 2D, or 3D (reshaped to 2D). Inputs with rank >= 4 (e.g. Anima's MLP activations, which are not reshaped to 3D the way the attention path is) fell through the `input_reshaped.ndim == 2` guard and reached scaled_mm as bf16, silently dispatching a bf16 kernel instead of FP8. Since MLP is roughly half the compute, the FP8 speedup was far below expectation. Generalize the existing 3D->2D reshape to any rank >= 3 (flatten the leading dims, keep the contraction dim) and reshape the output back to the original leading dims. 2D and 3D inputs are handled exactly as before; only rank >= 4 inputs change (now quantized instead of skipped). This matches the rank-agnostic handling already used by the training path (flatten(0, -2) / unflatten). Fixes #14595.	2026-07-09 22:30:26 -04:00
comfyanonymous	b7a648ca20	Try to fix the model reloading issue some people have. (#14822)	2026-07-09 16:39:01 -07:00
comfyanonymous	73e84d5ec8	Support convrot int4 models. (#14859) ... linear_dtype in comfy_quant metadata can be used to set if the int4 op does the matrix multiplication in int8 or int4, the default is int4 on GPUs that support it with fallback to int8 for GPUs that don't.	2026-07-09 18:57:09 -04:00
Alexis Rolland	1ea724339c	Update cla.yml (#14851)	2026-07-09 17:57:44 -04:00
Simon Pinfold	412aaab0e2	feat(api): expose registered extension filters on /experiment/models (#14797) ... Each folder in the listing now carries its registered extension allowlist verbatim; an empty array means the folder accepts any extension (match-all), mirroring filter_files_extensions semantics. Gives consumers the filtering rule itself rather than just its output: /models/{folder} lists files by the per-folder rule but the rule is not exposed anywhere, and /experiment/models/{folder} filters everything by the global supported_pt_extensions regardless of registration. Presentation-level filtering of match-all folders (e.g. hiding README/config noise that repository-downloading custom nodes leave in model directories) is deliberately left to the consumer. Co-authored-by: guill <jacob.e.segal@gmail.com>	2026-07-09 12:59:30 -07:00
Terry Jia	04a30fb375	fix: Load3D failing path validation from double path resolution (#14852)	2026-07-09 22:42:20 +08:00