29 Commits

Author	SHA1	Message	Date
Jedrzej Kosinski	5dc4e38b89	Defer @pollockjj's tiled-VAE and UPSCALE_MODEL MultiGPU lanes (#14066) ... * Revert "Add tiled VAE lane to MultiGPU Work Units" This reverts commit 4d3d68e473. The tiled VAE lane will land as part of a follow-up PR alongside the UPSCALE_MODEL lane, separated from the threaded-loader fix PR (#14052) to keep the upstream merge focused. * Revert "Add UPSCALE_MODEL lane to MultiGPU CFG Split" This reverts commit 74b0a826ea. The UPSCALE_MODEL lane will land as part of a follow-up PR alongside the tiled VAE lane, separated from the threaded-loader fix PR (#14052) to keep the upstream merge focused. --------- Co-authored-by: John Pollock <pollockjj@gmail.com>	2026-05-22 16:44:29 -07:00
John Pollock	74b0a826ea	Add UPSCALE_MODEL lane to MultiGPU CFG Split ... Introduce tiled_scale_multidim_multigpu in comfy/utils.py: a tile scheduler that dispatches per-device tile functions through the existing MultiGPUThreadPool and merges per-device CPU output buffers in deterministic key order. The worker only catches BaseException at the thread boundary to funnel errors to the main thread; bare torch.cuda.set_device and torch.cuda.synchronize calls inside the worker fail loud if the device is not CUDA, which is part of the primitive's contract. Add UPSCALE_MODEL input on the MultiGPU CFG Split node and an upscale-model descriptor deepclone helper in comfy/multigpu.py. Clones stay CPU-resident until execute time and are returned to CPU afterward. ImageUpscaleWithModel dispatches through tiled_scale_multidim_multigpu when a multigpu descriptor is attached; the single-device path runs unchanged when no clones are present.	2026-05-22 13:41:48 -05:00
comfyanonymous	a2840e7552	Make ImageUpscaleWithModel node work with intermediate device and dtype. (#13357)	2026-04-10 21:48:26 -04:00
rattus	535c16ce6e	Widen OOM_EXCEPTION to AcceleratorError form (#12835) ... Pytorch only filters for OOMs in its own allocators however there are paths that can OOM on allocators made outside the pytorch allocators. These manifest as an AllocatorError as pytorch does not have universal error translation to its OOM type on exception. Handle it. A log I have for this also shows a double report of the error async, so call the async discarder to cleanup and make these OOMs look like OOMs.	2026-03-10 00:41:02 -04:00
Christian Byrne	bdeac8897e	feat: Add search_aliases field to node schema (#12010) ... * feat: Add search_aliases field to node schema Adds `search_aliases` field to improve node discoverability. Users can define alternative search terms for nodes (e.g., "text concat" → StringConcatenate). Changes: - Add `search_aliases: list[str]` to V3 Schema - Add `SEARCH_ALIASES` support for V1 nodes - Include field in `/object_info` response - Add aliases to high-priority core nodes V1 usage: ```python class MyNode: SEARCH_ALIASES = ["alt name", "synonym"] ``` V3 usage: ```python io.Schema( node_id="MyNode", search_aliases=["alt name", "synonym"], ... ) ``` ## Related PRs - Frontend: Comfy-Org/ComfyUI_frontend#XXXX (draft - merge after this) - Docs: Comfy-Org/docs#XXXX (draft - merge after stable) * Propagate search_aliases through V3 Schema.get_v1_info to NodeInfoV1	2026-01-21 15:36:02 -08:00
comfyanonymous	38d0493825	Fix case where upscale model wouldn't be moved to cpu. (#11633)	2026-01-04 19:13:50 -05:00
Alexander Piskun	81e4dac107	convert nodes_upscale_model.py to V3 schema (#10149)	2025-10-09 16:08:40 -07:00
Chenlei Hu	0fd4e6c778	Lint unused import (#5973) ... * Lint unused import * nit * Remove unused imports * revert fix_torch import * nit	2024-12-09 15:24:39 -05:00
Alex "mcmonkey" Goodwin	254838f23c	add simple error check to model loading (#4950)	2024-09-17 03:57:17 -04:00
comfyanonymous	91542d4f8b	Import spandrel_extra_arches if present. ... I will not add this dependency to the default ones because models in the spandrel_extra_arches package are non commercial and therefore not compatible with free software licenses like the one ComfyUI uses. If you don't mind this you can install it manually yourself.	2024-05-28 01:42:11 -04:00
comfyanonymous	9a151b7def	Fix issue and unpin spandrel package.	2024-05-26 13:44:47 -04:00
Joey Ballentine	8cfd677cc0	Replace chainner_models with Spandrel package (#2146) ... * Replace chainner_models with Spandrel * Update to latest spandrel * Use spandrel_foss instead * update spandrel to new FOSS-compliant version	2024-05-26 13:44:17 -04:00
comfyanonymous	16eabdf70d	Free more vram for upscale models.	2024-04-25 17:04:19 -04:00
comfyanonymous	d09b5ef4ef	Free some memory before loading upscale models.	2024-04-22 18:51:15 -04:00
comfyanonymous	8be46438be	Support DiffBIR SwinIR models.	2023-09-07 03:31:43 -04:00
comfyanonymous	a51f33ee49	Use bigger tiles when upscaling with model and fallback on OOM.	2023-07-24 19:47:32 -04:00
comfyanonymous	587f89fe5a	Enable safe loading for upscale models.	2023-05-14 15:10:40 -04:00
comfyanonymous	fcf513e0b6	Refactor.	2023-05-03 17:48:35 -04:00
pythongosssss	5eeecf3fd5	remove unused import	2023-05-03 18:21:23 +01:00
pythongosssss	8912623ea9	use comfy progress bar	2023-05-03 18:19:22 +01:00
pythongosssss	06ad35b493	added progress to encode + upscale	2023-05-02 19:18:07 +01:00
comfyanonymous	73c3e11e83	Fix model_management import so it doesn't get executed twice.	2023-04-15 19:04:33 -04:00
comfyanonymous	809bcc8ceb	Add support for unCLIP SD2.x models. ... See _for_testing/unclip in the UI for the new nodes. unCLIPCheckpointLoader is used to load them. unCLIPConditioning is used to add the image cond and takes as input a CLIPVisionEncode output which has been moved to the conditioning section.	2023-04-01 23:19:15 -04:00
comfyanonymous	2e73367f45	Merge T2IAdapterLoader and ControlNetLoader. ... Workflows will be auto updated.	2023-03-17 18:17:59 -04:00
comfyanonymous	e1a9e26968	Add folder_paths so models can be in multiple paths.	2023-03-17 18:01:11 -04:00
comfyanonymous	494cfe5444	Prevent model_management from being loaded twice.	2023-03-15 15:18:18 -04:00
comfyanonymous	c8f1acc4eb	Put image upscaling nodes in image/upscaling category.	2023-03-11 18:10:36 -05:00
comfyanonymous	9db2e97b47	Tiled upscaling with the upscale models.	2023-03-11 14:04:13 -05:00
comfyanonymous	905857edd8	Take some code from chainner to implement ESRGAN and other upscale models.	2023-03-11 13:09:28 -05:00