4417 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Rattus	96ad4904fe	mm: fix debug message	2025-12-19 19:32:51 +10:00
Rattus	4bb34b85b7	mm: make model offloading deffered with weakrefs ... RAMPressure caching may ned to purge the same model that you are currently trying to offload for VRAM freeing. In this case, RAMPressure cache takes priority and needs to be able to pull the trigger on dumping the whole model and freeing the ModelPatcher in question. To do this, defer the actual tranfer of model weights from GPU to RAM to model_management state and not as part of ModelPatcher. This is dones as a list of weakrefs. If RAM cache decides to free to model you are currently unloading, then the ModelPatcher and refs simply dissappear in the middle of the unloading process, and both RAM and VRAM will be freed. The unpatcher now queues the individual leaf modules to be offloaded one-by-one so that RAM levels can be monitored. Note that the UnloadPartially that is potentially done as part of a load will not be freeable this way, however it shouldn't be anyway as that is the currently active model and RAM cache cannot save you if you cant even fit the one model you are currently trying to use.	2025-12-19 19:32:51 +10:00
Rattus	2c86040cf7	mm: dont use list of indexes for unload list work list ... This is currently put together as a list of indexes assuming the current_loaded_models doesn't change. However we might need to pruge a model as part of the offload process which means this list can change in the middle of the freeing process. handle by taking independent refs to the LoadedModel objects and dong safe by-value deletion of current_loaded_models.	2025-12-19 19:32:51 +10:00
Rattus	abe39647ee	mm: make garbage collector null safe on real_model ... currently this hard assumes that the caller of model_unload will keep current_loaded_models in sync. With RAMPressureCache its possible to have the garbage collector occur in the middle of the model free process which can split these two steps.	2025-12-19 19:32:51 +10:00
Rattus	3f4ee9174c	sd: Free RAM on main model load	2025-12-19 19:32:51 +10:00
Rattus	f190744f62	mm: Add free_ram() ... Add the free_ram() API and a means to install implementations of the freer (I.E. the RAM cache).	2025-12-19 19:32:51 +10:00
Rattus	4612aab281	caching: build headroom into the RAM cache ... move the headroom logic into the RAM cache to make this a little easier to call to "free me some RAM". Rename the API to free_ram(). Split off the clean_list creation to a completely separate function to avoid any stray strong reference to the content-to-be-freed on the stack.	2025-12-19 19:32:51 +10:00
comfyanonymous	894802b0f9	Add LatentCutToBatch node. (#11411)	2025-12-18 22:21:40 -05:00
comfyanonymous	28eaab608b	Diffusion model part of Qwen Image Layered. (#11408) ... Only thing missing after this is some nodes to make using it easier.	2025-12-18 20:21:14 -05:00
comfyanonymous	6a2678ac65	Trim/pad channels in VAE code. (#11406)	2025-12-18 18:22:38 -05:00
comfyanonymous	e4fb3a3572	Support loading Wan/Qwen VAEs with different in/out channels. (#11405)	2025-12-18 17:45:33 -05:00
ComfyUI Wiki	e8ebbe668e	chore: update workflow templates to v0.7.60 (#11403)	2025-12-18 17:09:29 -05:00
ric-yu	1ca89b810e	Add unified jobs API with /api/jobs endpoints (#11054) ... * feat: create a /jobs api to return queue and history jobs * update unused vars * include priority * create jobs helper file * fix ruff * update how we set error message * include execution error in both responses * rename error -> failed, fix output shape * re-use queue and history functions * set workflow id * allow srot by exec duration * fix tests * send priority and remove error msg * use ws messages to get start and end times * revert main.py fully * refactor: move all /jobs business logic to jobs.py * fix failing test * remove some tests * fix non dict nodes * address comments * filter by workflow id and remove null fields * add clearer typing - remove get("..") or .. * refactor query params to top get_job(s) doc, add remove_sensitive_from_queue * add brief comment explaining why we skip animated * comment that format field is for frontend backward compatibility * fix whitespace --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com> Co-authored-by: guill <jacob.e.segal@gmail.com>	2025-12-17 21:44:31 -08:00
comfyanonymous	bf7dc63bd6	skip_load_model -> force_full_load (#11390) ... This should be a bit more clear and less prone to potential breakage if the logic of the load models changes a bit.	2025-12-17 23:29:32 -05:00
Kohaku-Blueleaf	86dbb89fc9	Resolution bucketing and Trainer implementation refactoring (#11117)	2025-12-17 22:15:27 -05:00
comfyanonymous	ba6080bbab	ComfyUI v0.5.1	2025-12-17 21:04:50 -05:00
comfyanonymous	16d85ea133	Better handle torch being imported by prestartup nodes. (#11383)	2025-12-17 19:43:18 -05:00
chaObserv	5d9ad0c6bf	Fix the last step with non-zero sigma in sa_solver (#11380)	2025-12-17 13:57:40 -05:00
Alexander Piskun	c08f97f344	fix regression in V3 nodes processing (#11375)	2025-12-17 10:24:25 -08:00
Alexander Piskun	887143854b	feat(api-nodes): add GPT-Image-1.5 (#11368)	2025-12-17 09:43:41 -08:00
comfyanonymous	3a5f239cb6	ComfyUI v0.5.0	2025-12-17 03:46:11 -05:00
chaObserv	827bb1512b	Add exp_heun_2_x0 sampler series (#11360)	2025-12-16 23:35:43 -05:00
comfyanonymous	ffdd53b327	Check state dict key to auto enable the index_timestep_zero ref method. (#11362)	2025-12-16 17:03:17 -05:00
Alexander Piskun	65e2103b09	feat(api-nodes): add Wan2.6 model to video nodes (#11357)	2025-12-16 13:51:48 -08:00
Benjamin Lu	9304e47351	Update workflows for new release process (#11064) ... * Update release workflows for branch process * Adjust branch order in workflow triggers * Revert changes in test workflows	2025-12-15 23:24:18 -08:00
comfyanonymous	bc606d7d64	Add a way to set the default ref method in the qwen image code. (#11349)	2025-12-16 01:26:55 -05:00
comfyanonymous	645ee1881e	Inpainting for z image fun control. Use the ZImageFunControlnet node. (#11346) ... image -> control image ex: pose inpaint_image -> image for inpainting mask -> inpaint mask	2025-12-15 23:38:12 -05:00
Christian Byrne	3d082c3206	bump comfyui-frontend-package to 1.34.9 (patch) (#11342)	2025-12-15 23:35:37 -05:00
comfyanonymous	683569de55	Only enable fp16 on ZImage on newer pytorch. (#11344)	2025-12-15 22:33:27 -05:00
Haoming	ea2c117bc3	[BlockInfo] Wan (#10845) ... * block info * animate * tensor * device * revert	2025-12-15 17:59:16 -08:00
Haoming	fc4af86068	[BlockInfo] Lumina (#11227) ... * block info * device * Make tensor int again --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2025-12-15 17:57:28 -08:00
comfyanonymous	41bcf0619d	Add code to detect if a z image fun controlnet is broken or not. (#11341)	2025-12-15 20:51:06 -05:00
seed93	d02d0e5744	[add] tripo3.0 (#10663) ... * [add] tripo3.0 * [tripo] change paramter order * change order --------- Co-authored-by: liangd <liangding@vastai3d.com>	2025-12-15 17:38:46 -08:00
comfyanonymous	70541d4e77	Support the new qwen edit 2511 reference method. (#11340) ... index_timestep_zero can be selected in the FluxKontextMultiReferenceLatentMethod now with the display name set to the more generic "Edit Model Reference Method" node.	2025-12-15 19:20:34 -05:00
drozbay	77b2f7c228	Add context windows callback for custom cond handling (#11208) ... Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>	2025-12-15 16:06:32 -08:00
Alexander Piskun	43e0d4e3cc	comfy_api: remove usage of "Type","List" and "Dict" types (#11238)	2025-12-15 16:01:10 -08:00
Dr.Lt.Data	dbd330454a	feat(preview): add per-queue live preview method override (#11261) ... - Add set_preview_method() to override live preview method per queue item - Read extra_data.preview_method from /prompt request - Support values: taesd, latent2rgb, none, auto, default - "default" or unset uses server's CLI --preview-method setting - Add 44 tests (37 unit + 7 E2E)	2025-12-15 15:57:39 -08:00
Alexander Piskun	33c7f1179d	drop Pika API nodes (#11306)	2025-12-15 15:32:29 -08:00
Alexander Piskun	af91eb6c99	api-nodes: drop Kling v1 model (#11307)	2025-12-15 15:30:24 -08:00
comfyanonymous	5cb1e0c9a0	Disable guards on transformer_options when torch.compile (#11317)	2025-12-15 16:49:29 -05:00
ComfyUI Wiki	51347f9fb8	chore: update workflow templates to v0.7.59 (#11337)	2025-12-15 16:28:55 -05:00
Dr.Lt.Data	a5e85017d8	bump manager requirments to the 4.0.3b5 (#11324)	2025-12-15 14:24:01 -05:00
comfyanonymous	5ac3b26a7d	Update warning for old pytorch version. (#11319) ... Versions below 2.4 are no longer supported. We will not break support on purpose but will not fix it if we do.	2025-12-14 04:02:50 -05:00
chaObserv	6592bffc60	seeds_2: add phi_2 variant and sampler node (#11309) ... * Add phi_2 solver type to seeds_2 * Add sampler node of seeds_2	2025-12-14 00:03:29 -05:00
comfyanonymous	971cefe7d4	Fix pytorch warnings. (#11314)	2025-12-13 18:45:23 -05:00
comfyanonymous	da2bfb5b0a	Basic implementation of z image fun control union 2.0 (#11304) ... The inpaint part is currently missing and will be implemented later. I think they messed up this model pretty bad. They added some control_noise_refiner blocks but don't actually use them. There is a typo in their code so instead of doing control_noise_refiner -> control_layers it runs the whole control_layers twice. Unfortunately they trained with this typo so the model works but is kind of slow and would probably perform a lot better if they corrected their code and trained it again.	2025-12-13 01:39:11 -05:00
comfyanonymous	c5a47a1692	Fix bias dtype issue in mixed ops. (#11293)	2025-12-12 11:49:35 -05:00
Alexander Piskun	908fd7d749	feat(api-nodes): new TextToVideoWithAudio and ImageToVideoWithAudio nodes (#11267)	2025-12-12 00:18:31 -08:00
comfyanonymous	5495589db3	Respect the dtype the op was initialized in for non quant mixed op. (#11282)	2025-12-11 23:32:27 -05:00
Jukka Seppänen	982876d59a	WanMove support (#11247)	2025-12-11 22:29:34 -05:00