4925 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
ComfyUI Wiki	da29b797ce	Update workflow templates to v0.9.8 (#12788)	2026-03-05 07:23:23 -08:00
Alexander Piskun	9cdfd7403b	feat(api-nodes): enable Kling 3.0 Motion Control (#12785)	2026-03-05 07:12:38 -08:00
Alexander Piskun	bd21363563	feat(api-nodes-xAI): updated models, pricing, added features (#12756)	2026-03-05 04:29:39 -08:00
comfyanonymous	e04d0dbeb8	ComfyUI v0.16.0	2026-03-05 04:06:29 -05:00
ComfyUI Wiki	c8428541a6	chore: update workflow templates to v0.9.7 (#12780)	2026-03-05 03:58:25 -05:00
comfyanonymous	4941671b5a	Fix cuda getting initialized in cpu mode. (#12779)	2026-03-05 02:39:51 -05:00
ComfyUI Wiki	c5fe8ace68	chore: update workflow templates to v0.9.6 (#12778)	2026-03-05 02:37:35 -05:00
comfyanonymous	f2ee7f2d36	Fix cublas ops on dynamic vram. (#12776)	2026-03-05 01:21:55 -05:00
comfyanonymous	43c64b6308	Support the LTXAV 2.3 model. (#12773)	2026-03-04 20:06:20 -05:00
comfyanonymous	ac4a943ff3	Initial load device should be cpu when using dynamic vram. (#12766)	2026-03-04 16:33:14 -05:00
rattus	8811db52db	comfy-aimdo 0.2.6 (#12764) ... Comfy Aimdo 0.2.6 fixes a GPU virtual address leak. This would manfiest as an error after a number of workflow runs.	2026-03-04 12:12:37 -08:00
Jukka Seppänen	0a7446ade4	Pass tokens when loading text gen model for text generation (#12755) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-03-04 08:59:56 -08:00
rattus	9b85cf9558	Comfy Aimdo 0.2.5 + Fix offload performance in DynamicVram (#12754) ... * ops: dont unpin nothing This was calling into aimdo in the none case (offloaded weight). Whats worse, is aimdo syncs for unpinning an offloaded weight, as that is the corner case of a weight getting evicted by its own use which does require a sync. But this was heppening every offloaded weight causing slowdown. * mp: fix get_free_memory policy The ModelPatcherDynamic get_free_memory was deducting the model from to try and estimate the conceptual free memory with doing any offloading. This is kind of what the old memory_memory_required was estimating in ModelPatcher load logic, however in practical reality, between over-estimates and padding, the loader usually underloaded models enough such that sampling could send CFG +/- through together even when partially loaded. So don't regress from the status quo and instead go all in on the idea that offloading is less of an issue than debatching. Tell the sampler it can use everything.	2026-03-04 07:49:13 -08:00
rattus	d531e3fb2a	model_patcher: Improve dynamic offload heuristic (#12759) ... Define a threshold below which a weight loading takes priority. This actually makes the offload consistent with non-dynamic, because what happens, is when non-dynamic fills ints to_load list, it will fill-up any left-over pieces that could fix large weights with small weights and load them, even though they were lower priority. This actually improves performance because the timy weights dont cost any VRAM and arent worth the control overhead of the DMA etc.	2026-03-04 07:47:44 -08:00
B. Bergeron	b35b397720	Allow giving custom --extra-index-url, defaults to CU130	2026-03-04 00:32:27 -05:00
B. Bergeron	b3db4f5a7d	Split data volume	2026-03-04 00:32:27 -05:00
B. Bergeron	c8d94a8bb8	Improve documentation regarding pip install step	2026-03-04 00:32:27 -05:00
B. Bergeron	2aa8bb85bb	Improve documentation regarding numerical ownership	2026-03-04 00:32:26 -05:00
B. Bergeron	b8e087d8b9	Always update Python dependencies + don't hide pip logs	2026-03-04 00:32:26 -05:00
B. Bergeron	abea672ac8	Pin base image version to 3.12.12-trixie + document version choice	2026-03-04 00:32:26 -05:00
B. Bergeron	ea723833eb	Remove unused "AS" docker statement	2026-03-04 00:32:26 -05:00
B. Bergeron	a347690160	Remove superfluous interface binding	2026-03-04 00:32:26 -05:00
B. Bergeron	d95dd9aebe	Improved documentation	2026-03-04 00:32:26 -05:00
B. Bergeron	baeded5fee	Don't rebuild whole image when APT_EXTRA_PACKAGES changes	2026-03-04 00:32:26 -05:00
B. Bergeron	93a6e248e7	Fix permission issue on legacy builds	2026-03-04 00:32:26 -05:00
B. Bergeron	b6a2114d68	Use stable apt-get CLI interface instead of apt	2026-03-04 00:32:25 -05:00
B. Bergeron	a105334345	Use recommended compose file name for Docker Compose	2026-03-04 00:32:25 -05:00
B. Bergeron	5d57d5b244	Add @bbergeron0 to CODEOWNER	2026-03-04 00:32:25 -05:00
B. Bergeron	5225a36901	Remove superfluous command-separators	2026-03-04 00:32:25 -05:00
B. Bergeron	e8110604df	Force LF eol for entrypoint.sh	2026-03-04 00:32:25 -05:00
B. Bergeron	be635f2692	Update ownership of /comfyui to comfyui user	2026-03-04 00:32:25 -05:00
B. Bergeron	25c2362e8b	Inform user that installation might take a while	2026-03-04 00:32:25 -05:00
B. Bergeron	7caf2f116d	Install extra system dependencies at build-time	2026-03-04 00:32:25 -05:00
B. Bergeron	e3ab7e3cb0	Persist models installed by model managers	2026-03-04 00:32:24 -05:00
B. Bergeron	c5a42e7e1d	Add instructions for Docker installation	2026-03-04 00:32:24 -05:00
B. Bergeron	7d784d5049	Add local Docker support	2026-03-04 00:32:17 -05:00
Arthur R Longbottom	eb011733b6	Fix VideoFromComponents.save_to crash when writing to BytesIO (#12683) ... * Fix VideoFromComponents.save_to crash when writing to BytesIO When `get_container_format()` or `get_stream_source()` is called on a tensor-based video (VideoFromComponents), it calls `save_to(BytesIO())`. Since BytesIO has no file extension, `av.open` can't infer the output format and throws `ValueError: Could not determine output format`. The sibling class `VideoFromFile` already handles this correctly via `get_open_write_kwargs()`, which detects BytesIO and sets the format explicitly. `VideoFromComponents` just never got the same treatment. This surfaces when any downstream node validates the container format of a tensor-based video, like TopazVideoEnhance or any node that calls `validate_container_format_is_mp4()`. Three-line fix in `comfy_api/latest/_input_impl/video_types.py`. * Add docstring to save_to to satisfy CI coverage check	2026-03-04 00:29:00 -05:00
rattus	ac6513e142	DynamicVram: Add casting / fix torch Buffer weights (#12749) ... * respect model dtype in non-comfy caster * utils: factor out parent and name functionality of set_attr * utils: implement set_attr_buffer for torch buffers * ModelPatcherDynamic: Implement torch Buffer loading If there is a buffer in dynamic - force load it.	2026-03-03 18:19:40 -08:00
Terry Jia	b6ddc590ed	CURVE type (#12581) ... * CURVE type * fix: update typed wrapper unwrap keys to __type__ and __value__ * code improve * code improve	2026-03-03 16:58:53 -08:00
comfyanonymous	f719a9d928	Adjust memory usage factor of zeta model. (#12746)	2026-03-03 17:35:22 -05:00
rattus	174fd6759d	main: Load aimdo after logger is setup (#12743) ... This was too early. Aimdo can use the logger in error paths and this causes a rogue default init if aimdo has something to log.	2026-03-03 08:51:15 -08:00
rattus	09bcbddfcf	ModelPatcherDynamic: Force load all non-comfy weights (#12739) ... * model_management: Remove non-comfy dynamic _v caster * Force pre-load non-comfy weights to GPU in ModelPatcherDynamic Non-comfy weights may expect to be pre-cast to the target device without in-model casting. Previously they were allocated in the vbar with _v which required the _v fault path in cast_to. Instead, back up the original CPU weight and move it directly to GPU at load time.	2026-03-03 08:50:33 -08:00
xeinherjer	dff0a4a158	Fix VAEDecodeAudioTiled ignoring tile_size input (#12735) (#12738)	2026-03-02 20:17:51 -05:00
Lodestone	9ebee0a217	Feat: z-image pixel space (model still training atm) (#12709) ... * draft zeta (z-image pixel space) * revert gitignore * model loaded and able to run however vector direction still wrong tho * flip the vector direction to original again this time * Move wrongly positioned Z image pixel space class * inherit Radiance LatentFormat class * Fix parameters in classes for Zeta x0 dino * remove arbitrary nn.init instances * Remove unused import of lru_cache --------- Co-authored-by: silveroxides <ishimarukaito@gmail.com>	2026-03-02 19:43:47 -05:00
comfyanonymous	57dd6c1aad	Support loading zeta chroma weights properly. (#12734)	2026-03-02 18:54:18 -05:00
ComfyUI Wiki	f1f8996e15	chore: update workflow templates to v0.9.5 (#12732)	2026-03-02 09:13:42 -08:00
Alexander Piskun	afb54219fa	feat(api-nodes): allow to use "IMAGE+TEXT" in NanoBanana2 (#12729)	2026-03-01 23:24:33 -08:00
rattus	7175c11a4e	comfy aimdo 0.2.4 (#12727) ... Comfy Aimdo 0.2.4 fixes a VRAM buffer alignment issue that happens in someworkflows where action is able to bypass the pytorch allocator and go straight to the cuda hook.	2026-03-01 22:21:41 -08:00
rattus	dfbf99a061	model_mangament: make dynamic --disable-smart-memory work (#12724) ... This was previously considering the pool of dynamic models as one giant entity for the sake of smart memory, but that isnt really the useful or what a user would reasonably expect. Make Dynamic VRAM properly purge its models just like the old --disable-smart-memory but conditioning the dynamic-for-dynamic bypass on smart memory. Re-enable dynamic smart memory.	2026-03-01 19:18:56 -08:00
comfyanonymous	602f6bd82c	Make --disable-smart-memory disable dynamic vram. (#12722)	2026-03-01 15:28:39 -05:00