2270 Commits

Author	SHA1	Message	Date
Alexis Rolland	7ae6c41fcf	Merge branch 'master' into depth-anything_CORE-135	2026-06-10 04:08:00 +08:00
rattus	6f01b244a2	mm: dont reset cast buffers in cleanup_models_gc() (#14372) ... cleanup_models_gc can be called once per load_models_gpu via free_memory, which in turn can de-activate an active model via this reset_cast_buffers. cleanup_models_gc() could also come via obscure garbage collector paths so limit reset_cast_buffers to the post-node callsite instead.	2026-06-09 13:57:04 -04:00
Jukka Seppänen	184009c2f6	feat: Add model support for SCAIL-2 (#14373) ... * initial SCAIL2 support	2026-06-09 18:24:09 +03:00
kelseyee	07c53f8f0f	Add LoRA key mapping for LTXV/LTXAV models (#14349)	2026-06-09 09:57:58 -04:00
rattus	1639dc7a70	main/server: Add --debug-hang (#14371) ... Add an option to debug a hang with ctrl-C, dumping the backtraces to see where its stuck or slow.	2026-06-09 09:55:00 -04:00
Jukka Seppänen	8ed7f458d0	Allow custom templates with Ideogram4 TE (#14374)	2026-06-09 21:11:05 +08:00
Talmaj Marinc	9494456d33	Drop the in-code conversion of original DA3 models and add support for auto-detection of repackaged models.	2026-06-09 13:39:29 +02:00
Alexis Rolland	f89999289a	fix: Add back apply_rotary_emb for Qwen Image (#14364)	2026-06-09 11:55:49 +08:00
comfyanonymous	00b633f368	Revert "Add SeedVR2 support (CORE-6) (#14110)" (#14359) ... This reverts commit 7863cf0e53.	2026-06-08 18:00:20 -04:00
Talmaj Marinc	8cbdd8f72e	Use optimized attention in Dino2AttentionBlock.	2026-06-08 12:46:58 +02:00
John Pollock	7863cf0e53	Add SeedVR2 support (CORE-6) (#14110)	2026-06-08 18:15:05 +08:00
rattus	410df27253	Fix interoperation with external source of pinned memory pressure (#14252) ... * mm: split off registration helper to doer and headroom calc * pinned_memory: implement registration comfy side Move away from Aimdo buffer registrations which seem fraught with danger and do it comfy side. Just start with the basic move. * pinned_memory: do registrations as portable memory * pinned_memory: discard async errors on registration fail Like the good ol days. * pinned_memory: implement abs shortfall retry If pinned registration happens to fail despite the previous budget ensures, consider the allocation shortfall, ensure it again, and try again. This allows comfy pins to interoperate with other software that might be doing substantive pinning.	2026-06-05 08:39:35 -07:00
comfyanonymous	514bb8ba21	Fix ideogram if model dtype gets set to fp8. (#14291)	2026-06-04 19:20:22 -07:00
comfyanonymous	8e3045a90b	Memory usage factor for ideogram 4 on non dynamic vram. (#14264)	2026-06-03 12:19:18 -04:00
Jukka Seppänen	24f9a020ce	Support Ideogram4 (#14259)	2026-06-03 08:41:44 -07:00
comfyanonymous	d4c7ebff9c	Remove old useless no comfy kitchen fallback. (#14245) ... * Remove old fallback used when no comfy kitchen. * Remove unused logging import	2026-06-02 17:52:41 -07:00
Quasar of Mikus	e9207aa7cc	fix (MultiGPU): prevent freeze on manual abort when using MultiGPU CFG Split (#14235) ... * fix (MultiGPU): prevent freeze on manual abort when using MultiGPU CFG Split Problem: Upon manual abort application hangs indefinitely. `InterruptProcessingException` inherits from `BaseException` and bypasses MultiGPU's worker error handling block so thread dies silently, leaving the main thread waiting forever for `result_q.get()` Fix: Catch `comfy.model_management.InterruptProcessingException` instead of `Exception` so it's caught and passed back via `result_q` to unblock the main thread when manual abort signal fires. * oops	2026-06-02 10:05:24 -07:00
person4268	c96fcddb81	Radiance: support variant with nonzero txt_ids (#14206)	2026-06-01 22:07:48 -07:00
comfyanonymous	4b48535a7d	Do tripo dinov3 inference in fp32. (#14221)	2026-06-01 18:08:20 -07:00
comfyanonymous	e785f0d212	Some cast/dtype fixes for the birefnet and dino3 models. (#14217)	2026-06-01 14:35:26 -07:00
Talmaj Marinc	15f4dc401a	Switch to optimized_attention_for_device in camera DA3 module.	2026-06-01 16:11:04 +02:00
Talmaj Marinc	f57ebb4cf4	Simplify/remove duplication in detect_unet_config for Depth Anything 3	2026-06-01 16:11:04 +02:00
Talmaj Marinc	0d7fa3f5ab	Improve tooltips DA3	2026-06-01 16:11:04 +02:00
Talmaj Marinc	724bb7b525	Fix extrinsic quaternions by normalizing them to unit quaternion.	2026-06-01 16:11:04 +02:00
Talmaj Marinc	65e416fa2a	Move turbo to colormap.py and add it to DepthAnything3Render.	2026-06-01 16:11:04 +02:00
Talmaj Marinc	1ac1822c0a	Cleanup of comments.	2026-06-01 16:11:04 +02:00
Talmaj Marinc	8ff8b10c45	Remove unused code.	2026-06-01 16:11:04 +02:00
Talmaj Marinc	5568e15afb	Update DA3 to use dino2.get_intermediate_layers_da3	2026-06-01 16:11:04 +02:00
Talmaj Marinc	d5217129ef	Merge interpolate_pos_encoding method in dinov2	2026-06-01 16:11:04 +02:00
Talmaj Marinc	25ee627556	Fix ray_pose for non float32 dtypes CORE-135	2026-06-01 16:11:04 +02:00
Talmaj Marinc	3c47111bd4	Add support for pose estimation CORE-135.	2026-06-01 16:11:04 +02:00
Talmaj Marinc	1d5b6143e7	Refactor custom da dinov2 to image_encoders/dino2	2026-06-01 16:11:04 +02:00
Talmaj Marinc	a8c9ae9059	Modify upscaling to be closer to original CORE-135	2026-06-01 16:11:04 +02:00
Talmaj Marinc	137a05b93d	Initial commit CORE-135	2026-06-01 16:11:02 +02:00
Jukka Seppänen	462c27fdb2	feat: Add TripoSplat support (#14210)	2026-06-01 07:01:50 -07:00
savvadesogle	cd45f42a83	fix(multigpu): replace hardcoded torch.cuda.set_device with device-agnostic set_torch_device (#14191)	2026-05-30 21:18:42 -04:00
comfyanonymous	81aa5a38b2	Speed up ernie model by a bit on nvidia and use higher quality rope. (#14192)	2026-05-30 17:53:37 -07:00
rattus	f7297bc5a9	Revert deprecation of non-dynamic smart memory (CORE-152 (revert)) (#14183) ... * mm: re-instantate smart memory for VRAM * mm: restore non-dynamic smart memory By popular demand. We aren't quite ready for the deprecation as non dynamic enabled GPUs and some high-vram custom model loader setups prefer the old full hands on.	2026-05-30 15:20:33 -04:00
rattus	e154da83b1	Threaded Loader performance fixes / improvements (+ Aimdo 0.4.6) (#14116) ... * memory_management: Add direct to read GPU mode Make destination optional (or make it optionally GPU) and use aimdo to file_read direct to GPU. * ops: Remove stream pin buffers and use aimdo reads This consumed too much RAM and its better to just take the hit on the CPU syncing back the stream on a short ring buffer. Aimdo implements this so just rip the stream pin buffer from comfy. * model_management: all active pin registration movement Its better to just let the active model load past the pin limit as pins and let the pins move around. The saves the HDD and SATA people disk traffic while only costing a few GPU syncs. * utils: use aimdo file handle This opens on windows with more favourable flags * mp: only count the model proper for loaded_ram and vram Exclude live loras from the numbers to avoid the case where the reported loaded memory exceeds the size of the model. This causes me confusion in the Kijai visualizer when it looked fully loaded but was hitting disk due to this accounding disrepency. * utils: add bit reverse utility useful for max scattering something ordered. * pinned_memory: Implement offload balancing Use a max scatter alogorithm to prioritize pins of the same size such that when doing a little bit of offloading it gets scattered, allowing the prefetcher to more evenly swollow the offload. * comfy-aimdo 0.4.7 Aimdo 0.4.7 implement VRAM buffer exhaustion predection to avoid early speculative load of weights that definately wont fix once the inference gets further in. * model-prefetch: consolidate pin ensures on the sync point This could happen mid prefetch block, cause a sync of the entire block and lose overlap. Get ahead of the problem with a free down at the natural compute stream sync point. * mm: Put a 2GB min on the pin ceiling This is reasonably bad if it starts causing swap pressure, moreso than during normal ram-cache proceedings. Clamp it. * add --fast-disk	2026-05-30 15:20:04 -04:00
comfyanonymous	0b04660ba3	Speed up anima a bit on nvidia. (#14181)	2026-05-29 22:47:10 -07:00
comfyanonymous	6e1ef2311b	Remove useless code. (#14178)	2026-05-29 16:26:46 -07:00
Jukka Seppänen	54d5be4a8e	Fix background removal mask output shape (#14171)	2026-05-29 09:14:32 -07:00
rattus	684296148e	float: use CK stochastic rounding cuda kernel (#13971)	2026-05-28 19:23:42 -07:00
comfyanonymous	85a403d1ea	Disable sage attention in stable audio dit and VAE. (#14148)	2026-05-27 20:35:03 -04:00
Jukka Seppänen	987a937658	Support context window for PiD and fix lq_latent rounding (#14136)	2026-05-27 12:08:06 -07:00
comfyanonymous	e75a92c1b6	Add memory usage factor for lens model. (#14124)	2026-05-26 18:06:51 -07:00
comfyanonymous	d8d860a588	Closer memory usage factors for PID (#14123)	2026-05-26 18:04:55 -07:00
Jukka Seppänen	28f4ef277c	feat: Support NVIDIA PixelDiT and PiD (CORE-201) (#14103)	2026-05-26 17:50:14 -07:00
Jukka Seppänen	f9f54cae42	Lens: some cleanup (#14112) ... * Lens: remove redundant memory optimization	2026-05-26 10:32:53 +03:00
Jukka Seppänen	41812fa0ac	feat: Microsoft Lens support (CORE-248) (#14077)	2026-05-25 23:01:51 -07:00