2121 Commits

Author	SHA1	Message	Date
comfyanonymous	3041e5c354	Switch mochi and wan modes to use pytorch RMSNorm. (#7925) ... * Switch genmo model to native RMSNorm. * Switch WAN to native RMSNorm.	2025-05-03 19:07:55 -04:00
patientx	f98aad15d5	Merge branch 'comfyanonymous:master' into master	2025-05-02 23:58:33 +03:00
patientx	1068783ff8	Update zluda.py	2025-05-02 20:21:10 +03:00
patientx	3b827e0a59	Update zluda.py	2025-05-02 20:20:41 +03:00
Kohaku-Blueleaf	2ab9618732	Fix the bugs in OFT/BOFT moule (#7909) ... * Correct calculate_weight and load for OFT * Correct calculate_weight and loading for BOFT	2025-05-02 13:12:37 -04:00
patientx	bc1fa6e013	Create zluda.py (custom zluda for miopen-triton)	2025-05-02 17:44:26 +03:00
patientx	073ff4a11d	Create placeholder	2025-05-01 23:05:14 +03:00
patientx	aad001bfbe	Add files via upload	2025-05-01 23:04:46 +03:00
patientx	caa3597bb7	Create placeholder	2025-05-01 23:03:51 +03:00
patientx	085925ddf7	Update zluda.py	2025-05-01 20:49:28 +03:00
patientx	da173f67b3	Merge branch 'comfyanonymous:master' into master	2025-05-01 17:23:12 +03:00
comfyanonymous	aa9d759df3	Switch ltxv to use the pytorch RMSNorm. (#7897)	2025-05-01 06:33:42 -04:00
comfyanonymous	08ff5fa08a	Cleanup chroma PR.	2025-04-30 20:57:30 -04:00
Silver	4ca3d84277	Support for Chroma - Flux1 Schnell distilled with CFG (#7355) ... * Upload files for Chroma Implementation * Remove trailing whitespace * trim more trailing whitespace..oops * remove unused imports * Add supported_inference_dtypes * Set min_length to 0 and remove attention_mask=True * Set min_length to 1 * get_mdulations added from blepping and minor changes * Add lora conversion if statement in lora.py * Update supported_models.py * update model_base.py * add uptream commits * set modelType.FLOW, will cause beta scheduler to work properly * Adjust memory usage factor and remove unnecessary code * fix mistake * reduce code duplication * remove unused imports * refactor for upstream sync * sync chroma-support with upstream via syncbranch patch * Update sd.py * Add Chroma as option for the OptimalStepsScheduler node	2025-04-30 20:57:00 -04:00
patientx	f49d26848b	Merge branch 'comfyanonymous:master' into master	2025-04-30 13:46:06 +03:00
comfyanonymous	dbc726f80c	Better vace memory estimation. (#7875)	2025-04-29 20:42:00 -04:00
comfyanonymous	0a66d4b0af	Per device stream counters for async offload. (#7873)	2025-04-29 20:28:52 -04:00
patientx	64709ce55c	Merge branch 'comfyanonymous:master' into master	2025-04-29 14:18:45 +03:00
guill	68f0d35296	Add support for VIDEO as a built-in type (#7844) ... * Add basic support for videos as types This PR adds support for VIDEO as first-class types. In order to avoid unnecessary costs, VIDEO outputs must implement the `VideoInput` ABC, but their implementation details can vary. Included are two implementations of this type which can be returned by other nodes: * `VideoFromFile` - Created with either a path on disk (as a string) or a `io.BytesIO` containing the contents of a file in a supported format (like .mp4). This implementation won't actually load the video unless necessary. It will also avoid re-encoding when saving if possible. * `VideoFromComponents` - Created from an image tensor and an optional audio tensor. Currently, only h264 encoded videos in .mp4 containers are supported for saving, but the plan is to add additional encodings/containers in the near future (particularly .webm). * Add optimization to avoid parsing entire video * Improve type declarations to reduce warnings * Make sure bytesIO objects can be read many times * Fix a potential issue when saving long videos * Fix incorrect type annotation * Add a `LoadVideo` node to make testing easier * Refactor new types out of the base comfy folder I've created a new `comfy_api` top-level module. The intention is that anything within this folder would be covered by semver-style versioning that would allow custom nodes to rely on them not introducing breaking changes. * Fix linting issue	2025-04-29 05:58:00 -04:00
patientx	0aeb958ea5	Merge branch 'comfyanonymous:master' into master	2025-04-29 01:49:37 +03:00
comfyanonymous	83d04717b6	Support HiDream E1 model. (#7857)	2025-04-28 15:01:15 -04:00
chaObserv	c15909bb62	CFG++ for gradient estimation sampler (#7809)	2025-04-28 13:51:35 -04:00
comfyanonymous	5a50c3c7e5	Fix stream priority to support older pytorch. (#7856)	2025-04-28 13:07:21 -04:00
Pam	30159a7fe6	Save v pred zsnr metadata (#7840)	2025-04-28 13:03:21 -04:00
patientx	6244dfa1e1	Merge branch 'comfyanonymous:master' into master	2025-04-28 01:13:53 +03:00
comfyanonymous	c8cd7ad795	Use stream for casting if enabled. (#7833)	2025-04-27 05:38:11 -04:00
patientx	ec34f4da57	Merge branch 'comfyanonymous:master' into master	2025-04-27 05:01:55 +03:00
comfyanonymous	ac10a0d69e	Make loras work with --async-offload (#7824)	2025-04-26 19:56:22 -04:00
patientx	9cc8e2e1d0	Merge branch 'comfyanonymous:master' into master	2025-04-26 23:32:14 +03:00
comfyanonymous	0dcc75ca54	Add experimental --async-offload lowvram weight offloading. (#7820) ... This should speed up the lowvram mode a bit. It currently is only enabled when --async-offload is used but it will be enabled by default in the future if there are no problems.	2025-04-26 16:11:21 -04:00
patientx	d6238ed3f0	Merge branch 'comfyanonymous:master' into master	2025-04-26 15:31:39 +03:00
comfyanonymous	23e39f2ba7	Add a T5TokenizerOptions node to set options for the T5 tokenizer. (#7803)	2025-04-25 19:36:00 -04:00
patientx	57a5e6e7ae	Merge branch 'comfyanonymous:master' into master	2025-04-26 01:23:01 +03:00
AustinMroz	78992c4b25	[NodeDef] Add documentation on widgetType (#7768) ... * [NodeDef] Add documentation on widgetType * Document required version for widgetType	2025-04-25 13:35:07 -04:00
patientx	224f72f90f	Merge branch 'comfyanonymous:master' into master	2025-04-25 14:11:50 +03:00
comfyanonymous	f935d42d8e	Support SimpleTuner lycoris lora format for HiDream.	2025-04-25 03:11:14 -04:00
patientx	1d9338b4b9	Merge branch 'comfyanonymous:master' into master	2025-04-24 14:50:59 +03:00
thot experiment	e2eed9eb9b	throw away alpha channel in clip vision preprocessor (#7769) ... saves users having to explicitly discard the channel	2025-04-23 21:28:36 -04:00
patientx	d8a75b86e9	Update zluda.py	2025-04-24 03:11:46 +03:00
patientx	91d7a9d234	Merge branch 'comfyanonymous:master' into master	2025-04-23 12:41:27 +03:00
comfyanonymous	552615235d	Fix for dino lowvram. (#7748)	2025-04-23 04:12:52 -04:00
Robin Huang	0738e4ea5d	[API nodes] Add backbone for supporting api nodes in ComfyUI (#7745) ... * Add Ideogram generate node. * Add staging api. * COMFY_API_NODE_NAME node property * switch to boolean flag and use original node name for id * add optional to type * Add API_NODE and common error for missing auth token (#5) * Add Minimax Video Generation + Async Task queue polling example (#6) * [Minimax] Show video preview and embed workflow in ouput (#7) * [API Nodes] Send empty request body instead of empty dictionary. (#8) * Fixed: removed function from rebase. * Add pydantic. * Remove uv.lock * Remove polling operations. * Update stubs workflow. * Remove polling comments. * Update stubs. * Use pydantic v2. * Use pydantic v2. * Add basic OpenAITextToImage node * Add. * convert image to tensor. * Improve types. * Ruff. * Push tests. * Handle multi-form data. - Don't set content-type for multi-part/form - Use data field instead of JSON * Change to api.comfy.org * Handle error code 409. * Remove nodes. --------- Co-authored-by: bymyself <cbyrne@comfy.org> Co-authored-by: Yoland Y <4950057+yoland68@users.noreply.github.com>	2025-04-23 02:18:08 -04:00
patientx	a397c3aeb3	Merge branch 'comfyanonymous:master' into master	2025-04-22 13:28:29 +03:00
comfyanonymous	2d6805ce57	Add option for using fp8_e8m0fnu for model weights. (#7733) ... Seems to break every model I have tried but worth testing?	2025-04-22 06:17:38 -04:00
patientx	c09fa908f5	Merge branch 'comfyanonymous:master' into master	2025-04-22 12:13:56 +03:00
Kohaku-Blueleaf	a8f63c0d5b	Support dora_scale on both axis (#7727)	2025-04-22 05:01:27 -04:00
Kohaku-Blueleaf	966c43ce26	Add OFT/BOFT algorithm in weight adapter (#7725)	2025-04-22 04:59:47 -04:00
comfyanonymous	3ab231f01f	Fix issue with WAN VACE implementation. (#7724)	2025-04-21 23:36:12 -04:00
Kohaku-Blueleaf	1f3fba2af5	Unified Weight Adapter system for better maintainability and future feature of Lora system (#7540)	2025-04-21 20:15:32 -04:00
comfyanonymous	5d0d4ee98a	Add strength control for vace. (#7717)	2025-04-21 19:36:20 -04:00
patientx	32ec658779	Merge branch 'comfyanonymous:master' into master	2025-04-21 23:16:54 +03:00
filtered	5d51794607	Add node type hint for socketless option (#7714) ... * Add node type hint for socketless option * nit - Doc	2025-04-21 16:13:00 -04:00
comfyanonymous	ce22f687cc	Support for WAN VACE preview model. (#7711) ... * Support for WAN VACE preview model. * Remove print.	2025-04-21 14:40:29 -04:00
patientx	d926896b55	Merge branch 'comfyanonymous:master' into master	2025-04-21 00:00:31 +03:00
comfyanonymous	2c735c13b4	Slightly better fix for #7687	2025-04-20 11:33:27 -04:00
patientx	0143b19681	Merge branch 'comfyanonymous:master' into master	2025-04-20 15:05:36 +03:00
comfyanonymous	fd27494441	Use empty t5 of size 128 for hidream, seems to give closer results.	2025-04-19 19:49:40 -04:00
power88	f43e1d7f41	Hidream: Allow loading hidream text encoders in CLIPLoader and DualCLIPLoader (#7676) ... * Hidream: Allow partial loading text encoders * reformat code for ruff check.	2025-04-19 19:47:30 -04:00
patientx	cd77ded0c7	Merge branch 'comfyanonymous:master' into master	2025-04-19 23:20:10 +03:00
comfyanonymous	636d4bfb89	Fix hard crash when the spiece tokenizer path is bad.	2025-04-19 15:55:43 -04:00
patientx	682a70bcf9	Update zluda.py	2025-04-19 00:53:59 +03:00
patientx	71ac9830ab	updated comfyui-frontend version	2025-04-17 22:15:11 +03:00
patientx	95773a0045	updated "comfyui-frontend version" - added "comfyui-workflow-templates"	2025-04-17 22:13:36 +03:00
patientx	d9211bbf1e	Merge branch 'comfyanonymous:master' into master	2025-04-17 20:51:12 +03:00
comfyanonymous	dbcfd092a2	Set default context_img_len to 257	2025-04-17 12:42:34 -04:00
comfyanonymous	c14429940f	Support loading WAN FLF model.	2025-04-17 12:04:48 -04:00
patientx	6bbe3b19d4	Merge branch 'comfyanonymous:master' into master	2025-04-17 14:51:08 +03:00
comfyanonymous	0d720e4367	Don't hardcode length of context_img in wan code.	2025-04-17 06:25:39 -04:00
patientx	7950c510e7	Merge branch 'comfyanonymous:master' into master	2025-04-17 10:10:03 +03:00
comfyanonymous	1fc00ba4b6	Make hidream work with any latent resolution.	2025-04-16 18:34:14 -04:00
patientx	d05e9b8298	Merge branch 'comfyanonymous:master' into master	2025-04-17 01:22:11 +03:00
comfyanonymous	9899d187b1	Limit T5 to 128 tokens for HiDream: #7620	2025-04-16 18:07:55 -04:00
comfyanonymous	f00f340a56	Reuse code from flux model.	2025-04-16 17:43:55 -04:00
patientx	503292b3c0	Merge branch 'comfyanonymous:master' into master	2025-04-16 23:26:10 +03:00
Chenlei Hu	cce1d9145e	[Type] Mark input options NotRequired (#7614)	2025-04-16 15:41:00 -04:00
patientx	765224ad78	Merge branch 'comfyanonymous:master' into master	2025-04-16 12:10:01 +03:00
comfyanonymous	b4dc03ad76	Fix issue on old torch.	2025-04-16 04:53:56 -04:00
patientx	eee802e685	Update zluda.py	2025-04-16 00:53:18 +03:00
patientx	ad2fa1a675	Merge branch 'comfyanonymous:master' into master	2025-04-16 00:50:26 +03:00
comfyanonymous	9ad792f927	Basic support for hidream i1 model.	2025-04-15 17:35:05 -04:00
patientx	ab0860b96a	Merge branch 'comfyanonymous:master' into master	2025-04-15 21:37:22 +03:00
comfyanonymous	6fc5dbd52a	Cleanup.	2025-04-15 12:13:28 -04:00
patientx	af58afcae8	Merge branch 'comfyanonymous:master' into master	2025-04-15 18:23:31 +03:00
comfyanonymous	3e8155f7a3	More flexible long clip support. ... Add clip g long clip support. Text encoder refactor. Support llama models with different vocab sizes.	2025-04-15 10:32:21 -04:00
patientx	09491fecbd	Merge branch 'comfyanonymous:master' into master	2025-04-15 14:41:15 +03:00
comfyanonymous	8a438115fb	add RMSNorm to comfy.ops	2025-04-14 18:00:33 -04:00
patientx	205bdad97e	fix frontend package version	2025-04-13 17:12:14 +03:00
patientx	b6d5765f0f	Added onnxruntime patching	2025-04-13 17:11:13 +03:00
patientx	f1513262d3	Merge branch 'comfyanonymous:master' into master	2025-04-13 03:21:00 +03:00
chaObserv	e51d9ba5fc	Add SEEDS (stage 2 & 3 DP) sampler (#7580) ... * Add seeds stage 2 & 3 (DP) sampler * Change the name to SEEDS in comment	2025-04-12 18:36:08 -04:00
catboxanon	1714a4c158	Add CublasOps support (#7574) ... * CublasOps support * Guard CublasOps behind --fast arg	2025-04-12 18:29:15 -04:00
patientx	81b9fcfe4d	Merge branch 'comfyanonymous:master' into master	2025-04-11 19:55:56 +03:00
Chargeuk	ed945a1790	Dependency Aware Node Caching for low RAM/VRAM machines (#7509) ... * add dependency aware cache that removed a cached node as soon as all of its decendents have executed. This allows users with lower RAM to run workflows they would otherwise not be able to run. The downside is that every workflow will fully run each time even if no nodes have changed. * remove test code * tidy code	2025-04-11 06:55:51 -04:00
patientx	163780343e	updated comfyui-frontend version	2025-04-11 00:32:22 +03:00
patientx	27f850ff8a	Merge branch 'comfyanonymous:master' into master	2025-04-11 00:23:38 +03:00
Chenlei Hu	98bdca4cb2	Deprecate InputTypeOptions.defaultInput (#7551) ... * Deprecate InputTypeOptions.defaultInput * nit * nit	2025-04-10 06:57:06 -04:00
patientx	ae8488fdc7	Merge branch 'comfyanonymous:master' into master	2025-04-09 19:53:21 +03:00
Jedrzej Kosinski	e346d8584e	Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape (#7500)	2025-04-09 09:43:35 -04:00
patientx	2bf016391a	Merge branch 'comfyanonymous:master' into master	2025-04-07 13:01:39 +03:00
comfyanonymous	70d7242e57	Support the wan fun reward loras.	2025-04-07 05:01:47 -04:00
patientx	137ab318e1	Merge branch 'comfyanonymous:master' into master	2025-04-05 16:30:54 +03:00
comfyanonymous	3bfe4e5276	Support 512 siglip model.	2025-04-05 07:01:01 -04:00
patientx	c90f1b7948	Merge branch 'comfyanonymous:master' into master	2025-04-05 13:39:32 +03:00
Raphael Walker	89e4ea0175	Add activations_shape info in UNet models (#7482) ... * Add activations_shape info in UNet models * activations_shape should be a list	2025-04-04 21:27:54 -04:00
comfyanonymous	3a100b9a55	Disable partial offloading of audio VAE.	2025-04-04 21:24:56 -04:00
patientx	4541842b9a	Merge branch 'comfyanonymous:master' into master	2025-04-03 03:15:32 +03:00
BiologicalExplosion	2222cf67fd	MLU memory optimization (#7470) ... Co-authored-by: huzhan <huzhan@cambricon.com>	2025-04-02 19:24:04 -04:00
patientx	1040220970	Merge branch 'comfyanonymous:master' into master	2025-04-01 22:56:01 +03:00
BVH	301e26b131	Add option to store TE in bf16 (#7461)	2025-04-01 13:48:53 -04:00
patientx	b7d9be6864	Merge branch 'comfyanonymous:master' into master	2025-03-30 14:17:07 +03:00
comfyanonymous	a3100c8452	Remove useless code.	2025-03-29 20:12:56 -04:00
patientx	f02045a45d	Merge branch 'comfyanonymous:master' into master	2025-03-28 16:58:48 +03:00
comfyanonymous	2d17d8910c	Don't error if wan concat image has extra channels.	2025-03-28 08:49:29 -04:00
patientx	01f2da55f9	Update zluda.py	2025-03-28 10:33:39 +03:00
patientx	9d401fe602	Merge branch 'comfyanonymous:master' into master	2025-03-27 22:52:53 +03:00
comfyanonymous	0a1f8869c9	Add WanFunInpaintToVideo node for the Wan fun inpaint models.	2025-03-27 11:13:27 -04:00
patientx	39cf3cdc32	Merge branch 'comfyanonymous:master' into master	2025-03-27 12:35:23 +03:00
comfyanonymous	3661c833bc	Support the WAN 2.1 fun control models. ... Use the new WanFunControlToVideo node.	2025-03-26 19:54:54 -04:00
patientx	8115bdf68a	Merge branch 'comfyanonymous:master' into master	2025-03-25 22:35:14 +03:00
comfyanonymous	8edc1f44c1	Support more float8 types.	2025-03-25 05:23:49 -04:00
patientx	87e937ecd6	Merge branch 'comfyanonymous:master' into master	2025-03-23 18:32:46 +03:00
comfyanonymous	e471c726e5	Fallback to pytorch attention if sage attention fails.	2025-03-22 15:45:56 -04:00
patientx	64008960e9	Update zluda.py	2025-03-22 13:53:47 +03:00
patientx	a6db9cc07a	Merge branch 'comfyanonymous:master' into master	2025-03-22 13:52:43 +03:00
comfyanonymous	d9fa9d307f	Automatically set the right sampling type for lotus.	2025-03-21 14:19:37 -04:00
thot experiment	83e839a89b	Native LotusD Implementation (#7125) ... * draft pass at a native comfy implementation of Lotus-D depth and normal est * fix model_sampling kludges * fix ruff --------- Co-authored-by: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>	2025-03-21 14:04:15 -04:00
patientx	cf9ad7aae3	Update zluda.py	2025-03-21 12:21:23 +03:00
patientx	28a4de830c	Merge branch 'comfyanonymous:master' into master	2025-03-20 14:23:30 +03:00
comfyanonymous	3872b43d4b	A few fixes for the hunyuan3d models.	2025-03-20 04:52:31 -04:00
comfyanonymous	32ca0805b7	Fix orientation of hunyuan 3d model.	2025-03-19 19:55:24 -04:00
comfyanonymous	11f1b41bab	Initial Hunyuan3Dv2 implementation. ... Supports the multiview, mini, turbo models and VAEs.	2025-03-19 16:52:58 -04:00
patientx	4115126a82	Update zluda.py	2025-03-19 12:15:38 +03:00
patientx	34b87d4542	Merge branch 'comfyanonymous:master' into master	2025-03-18 17:14:19 +03:00
comfyanonymous	3b19fc76e3	Allow disabling pe in flux code for some other models.	2025-03-18 05:09:25 -04:00
patientx	c853489349	Merge branch 'comfyanonymous:master' into master	2025-03-18 01:12:05 +03:00
comfyanonymous	50614f1b79	Fix regression with clip vision.	2025-03-17 13:56:11 -04:00
patientx	97dd7b8b52	Merge branch 'comfyanonymous:master' into master	2025-03-17 13:10:34 +03:00
comfyanonymous	6dc7b0bfe3	Add support for giant dinov2 image encoder.	2025-03-17 05:53:54 -04:00
patientx	30e3177e00	Merge branch 'comfyanonymous:master' into master	2025-03-16 21:26:31 +03:00
comfyanonymous	e8e990d6b8	Cleanup code.	2025-03-16 06:29:12 -04:00
patientx	dcc409faa4	Merge branch 'comfyanonymous:master' into master	2025-03-16 13:05:56 +03:00
Jedrzej Kosinski	2e24a15905	Call unpatch_hooks at the start of ModelPatcher.partially_unload (#7253) ... * Call unpatch_hooks at the start of ModelPatcher.partially_unload * Only call unpatch_hooks in partially_unload if lowvram is possible	2025-03-16 06:02:45 -04:00
chaObserv	fd5297131f	Guard the edge cases of noise term in er_sde (#7265)	2025-03-16 06:02:25 -04:00
patientx	bc664959a4	Merge branch 'comfyanonymous:master' into master	2025-03-15 17:11:51 +03:00
comfyanonymous	55a1b09ddc	Allow loading diffusion model files with the "Load Checkpoint" node.	2025-03-15 08:27:49 -04:00
comfyanonymous	3c3988df45	Show a better error message if the VAE is invalid.	2025-03-15 08:26:36 -04:00
comfyanonymous	a2448fc527	Remove useless code.	2025-03-14 18:10:37 -04:00
patientx	977dbafcf6	update the comfyui frontend package version	2025-03-15 00:07:04 +03:00
patientx	ccd9fe7f3c	Merge branch 'comfyanonymous:master' into master	2025-03-14 23:47:51 +03:00
comfyanonymous	6a0daa79b6	Make the SkipLayerGuidanceDIT node work on WAN.	2025-03-14 10:55:19 -04:00
FeepingCreature	9c98c6358b	Tolerate missing @torch.library.custom_op (#7234) ... This can happen on Pytorch versions older than 2.4.	2025-03-14 09:51:26 -04:00
patientx	bcea9b9a0c	Update attention.py to keep older torch versions running	2025-03-14 16:45:32 +03:00
patientx	eaf40b802d	Merge branch 'comfyanonymous:master' into master	2025-03-14 12:00:25 +03:00
FeepingCreature	7aceb9f91c	Add --use-flash-attention flag. (#7223) ... * Add --use-flash-attention flag. This is useful on AMD systems, as FA builds are still 10% faster than Pytorch cross-attention.	2025-03-14 03:22:41 -04:00
comfyanonymous	35504e2f93	Fix.	2025-03-13 15:03:18 -04:00
comfyanonymous	299436cfed	Print mac version.	2025-03-13 10:05:40 -04:00
patientx	b57a624e7c	Merge branch 'comfyanonymous:master' into master	2025-03-13 03:13:15 +03:00
Chenlei Hu	9b6cd9b874	[NodeDef] Add documentation on multi_select input option (#7212)	2025-03-12 17:29:39 -04:00
chaObserv	3fc688aebd	Ensure the extra_args in dpmpp sde series (#7204)	2025-03-12 17:28:59 -04:00
patientx	4a632a54a4	Merge branch 'comfyanonymous:master' into master	2025-03-12 11:28:56 +03:00
chaObserv	01015bff16	Add er_sde sampler (#7187)	2025-03-12 02:42:37 -04:00
patientx	cf490d92b3	Merge branch 'comfyanonymous:master' into master	2025-03-11 01:28:12 +03:00
comfyanonymous	ca8efab79f	Support control loras on Wan.	2025-03-10 17:23:13 -04:00
patientx	c469113159	Merge branch 'comfyanonymous:master' into master	2025-03-09 14:09:50 +03:00
comfyanonymous	9aac21f894	Fix issues with new hunyuan img2vid model and bumb version to v0.3.26	2025-03-09 05:07:22 -04:00
Jedrzej Kosinski	528d1b3563	When cached_hook_patches contain weights for hooks, only use hook_backup for unused keys (#7067)	2025-03-09 04:26:31 -04:00
comfyanonymous	7395b0c0d1	Support new hunyuan video i2v model. ... Use the new "v2 (replace)" guidance type in HunyuanImageToVideo and set image_interleave to 4 on the "Text Encode Hunyuan Video" node.	2025-03-08 20:34:47 -05:00
comfyanonymous	0952569493	Fix stable cascade VAE on some lowvram machines.	2025-03-08 20:24:04 -05:00
patientx	b8ad97eca2	Update zluda.py	2025-03-08 14:57:09 +03:00
patientx	0bf4f88dea	Update zluda.py	2025-03-08 14:37:15 +03:00
patientx	2ce9177547	Update zluda.py	2025-03-08 14:33:15 +03:00
patientx	0f7de5c588	Update zluda.py	2025-03-08 14:23:08 +03:00
patientx	d385e286a1	Update zluda.py	2025-03-08 14:22:23 +03:00
patientx	09156b577c	Merge branch 'comfyanonymous:master' into master	2025-03-08 14:21:36 +03:00
comfyanonymous	be4e760648	Add an image_interleave option to the Hunyuan image to video encode node. ... See the tooltip for what it does.	2025-03-07 19:56:26 -05:00
patientx	8847252eec	Merge branch 'comfyanonymous:master' into master	2025-03-07 16:14:21 +03:00
comfyanonymous	11b1f27cb1	Set WAN default compute dtype to fp16.	2025-03-07 04:52:36 -05:00
comfyanonymous	70e15fd743	No need for scale_input when fp8 matrix mult is disabled.	2025-03-07 04:49:20 -05:00
comfyanonymous	e1474150de	Support fp8_scaled diffusion models that don't use fp8 matrix mult.	2025-03-07 04:39:21 -05:00
patientx	7d16d06c3b	Merge branch 'comfyanonymous:master' into master	2025-03-06 23:42:01 +03:00
JettHu	e62d72e8ca	Typo in node_typing.py (#7092)	2025-03-06 15:24:04 -05:00
patientx	03825eaa28	Merge branch 'comfyanonymous:master' into master	2025-03-06 22:23:13 +03:00
comfyanonymous	dfa36e6855	Fix some things breaking when embeddings fail to apply.	2025-03-06 13:31:55 -05:00
patientx	44c060b3de	Merge branch 'comfyanonymous:master' into master	2025-03-06 12:16:31 +03:00
comfyanonymous	29a70ca101	Support HunyuanVideo image to video model.	2025-03-06 03:07:15 -05:00
comfyanonymous	0bef826a98	Support llava clip vision model.	2025-03-06 00:24:43 -05:00
comfyanonymous	85ef295069	Make applying embeddings more efficient. ... Adding new tokens no longer makes a whole copy of the embeddings weight which can be massive on certain models.	2025-03-05 17:34:38 -05:00
patientx	199e91029d	Merge branch 'comfyanonymous:master' into master	2025-03-05 23:54:19 +03:00
Chenlei Hu	5d84607bf3	Add type hint for FileLocator (#6968) ... * Add type hint for FileLocator * nit	2025-03-05 15:35:26 -05:00
Silver	c1909f350f	Better argument handling of front-end-root (#7043) ... * Better argument handling of front-end-root Improves handling of front-end-root launch argument. Several instances where users have set it and ComfyUI launches as normal and completely disregards the launch arg which doesn't make sense. Better to indicate to user that something is incorrect. * Removed unused import There was no real reason to use "Optional" typing in ther front-end-root argument.	2025-03-05 15:34:22 -05:00
Chenlei Hu	52b3469606	[NodeDef] Explicitly add control_after_generate to seed/noise_seed (#7059) ... * [NodeDef] Explicitly add control_after_generate to seed/noise_seed * Update comfy/comfy_types/node_typing.py Co-authored-by: filtered <176114999+webfiltered@users.noreply.github.com> --------- Co-authored-by: filtered <176114999+webfiltered@users.noreply.github.com>	2025-03-05 15:33:23 -05:00
patientx	c36a942c12	Merge branch 'comfyanonymous:master' into master	2025-03-05 19:11:25 +03:00
comfyanonymous	369b079ff6	Fix lowvram issue with ltxv vae.	2025-03-05 05:26:08 -05:00
comfyanonymous	9c9a7f012a	Adjust ltxv memory factor.	2025-03-05 05:16:05 -05:00
patientx	93001919fa	Merge branch 'comfyanonymous:master' into master	2025-03-05 11:17:58 +03:00
comfyanonymous	93fedd92fe	Support LTXV 0.9.5. ... Credits: Lightricks team.	2025-03-05 00:13:49 -05:00
patientx	586eabb95d	Merge branch 'comfyanonymous:master' into master	2025-03-04 19:10:54 +03:00
comfyanonymous	65042f7d39	Make it easier to set a custom template for hunyuan video.	2025-03-04 09:26:05 -05:00
patientx	cacb8da101	Merge branch 'comfyanonymous:master' into master	2025-03-04 13:17:37 +03:00
comfyanonymous	7c7c70c400	Refactor skyreels i2v code.	2025-03-04 00:15:45 -05:00
patientx	f12bcde392	Merge branch 'comfyanonymous:master' into master	2025-03-03 15:10:56 +03:00
comfyanonymous	f86c724ef2	Temporal area composition. ... New ConditioningSetAreaPercentageVideo node.	2025-03-03 06:50:31 -05:00
patientx	6c34d0a58a	Update zluda.py	2025-03-02 22:43:11 +03:00
patientx	7763bf823e	Merge branch 'comfyanonymous:master' into master	2025-03-02 17:18:12 +03:00
comfyanonymous	9af6320ec9	Make 2d area composition nodes work on video models.	2025-03-02 08:19:16 -05:00
patientx	0c4bebf5fb	Merge branch 'comfyanonymous:master' into master	2025-03-01 14:59:20 +03:00
comfyanonymous	4dc6709307	Rename argument in last commit and document the options.	2025-03-01 02:43:49 -05:00
Chenlei Hu	4d55f16ae8	Use enum list for --fast options (#7024)	2025-03-01 02:37:35 -05:00
patientx	c235a51d82	Update zluda.py	2025-02-28 16:41:56 +03:00
patientx	af43425ab5	Update model_management.py	2025-02-28 16:37:55 +03:00
patientx	1871a594ba	Merge branch 'comfyanonymous:master' into master	2025-02-28 11:47:19 +03:00
comfyanonymous	cf0b549d48	--fast now takes a number as argument to indicate how fast you want it. ... The idea is that you can indicate how much quality vs speed you want. At the moment: --fast 2 enables fp16 accumulation if your pytorch supports it. --fast 5 enables fp8 matrix mult on fp8 models and the optimization above. --fast without a number enables all optimizations.	2025-02-28 02:48:20 -05:00
comfyanonymous	eb4543474b	Use fp16 for intermediate for fp8 weights with --fast if supported.	2025-02-28 02:17:50 -05:00
comfyanonymous	1804397952	Use fp16 if checkpoint weights are fp16 and the model supports it.	2025-02-27 16:39:57 -05:00
patientx	cc65ca4c42	Merge branch 'comfyanonymous:master' into master	2025-02-28 00:39:40 +03:00
comfyanonymous	f4dac8ab6f	Wan code small cleanup.	2025-02-27 07:22:42 -05:00
patientx	c4fb9f2a63	Merge branch 'comfyanonymous:master' into master	2025-02-27 13:06:17 +03:00
BiologicalExplosion	89253e9fe5	Support Cambricon MLU (#6964) ... Co-authored-by: huzhan <huzhan@cambricon.com>	2025-02-26 20:45:13 -05:00
comfyanonymous	3ea3bc8546	Fix wan issues when prompt length is long.	2025-02-26 20:34:02 -05:00
patientx	b04a1f4127	Merge branch 'comfyanonymous:master' into master	2025-02-27 01:24:29 +03:00
comfyanonymous	0270a0b41c	Reduce artifacts on Wan by doing the patch embedding in fp32.	2025-02-26 16:59:26 -05:00
patientx	4f968c3c56	Merge branch 'comfyanonymous:master' into master	2025-02-26 17:11:50 +03:00
comfyanonymous	c37f15f98e	Add fast preview support for Wan models.	2025-02-26 08:56:23 -05:00
patientx	1193f3fbb1	Merge branch 'comfyanonymous:master' into master	2025-02-26 16:47:39 +03:00
comfyanonymous	4bca7367f3	Don't try to use clip_fea on t2v model.	2025-02-26 08:38:09 -05:00
patientx	debf69185c	Merge branch 'comfyanonymous:master' into master	2025-02-26 16:00:33 +03:00
comfyanonymous	b6fefe686b	Better wan memory estimation.	2025-02-26 07:51:22 -05:00
patientx	583f140eda	Merge branch 'comfyanonymous:master' into master	2025-02-26 13:26:25 +03:00
comfyanonymous	fa62287f1f	More code reuse in wan. ... Fix bug when changing the compute dtype on wan.	2025-02-26 05:22:29 -05:00
patientx	743996a1f7	Merge branch 'comfyanonymous:master' into master	2025-02-26 12:56:06 +03:00
comfyanonymous	0844998db3	Slightly better wan i2v mask implementation.	2025-02-26 03:49:50 -05:00
comfyanonymous	4ced06b879	WIP support for Wan I2V model.	2025-02-26 01:49:43 -05:00
patientx	1e91ff59a1	Merge branch 'comfyanonymous:master' into master	2025-02-26 09:24:15 +03:00
comfyanonymous	cb06e9669b	Wan seems to work with fp16.	2025-02-25 21:37:12 -05:00
patientx	6e894524e2	Merge branch 'comfyanonymous:master' into master	2025-02-26 04:14:10 +03:00
comfyanonymous	9a66bb972d	Make wan work with all latent resolutions. ... Cleanup some code.	2025-02-25 19:56:04 -05:00
patientx	4269943ac3	Merge branch 'comfyanonymous:master' into master	2025-02-26 03:13:47 +03:00
comfyanonymous	ea0f939df3	Fix issue with wan and other attention implementations.	2025-02-25 19:13:39 -05:00
comfyanonymous	f37551c1d2	Change wan rope implementation to the flux one. ... Should be more compatible.	2025-02-25 19:11:14 -05:00
patientx	879db7bdfc	Merge branch 'comfyanonymous:master' into master	2025-02-26 02:07:25 +03:00
comfyanonymous	63023011b9	WIP support for Wan t2v model.	2025-02-25 17:20:35 -05:00
patientx	6cf0fdcc3c	Merge branch 'comfyanonymous:master' into master	2025-02-25 17:12:14 +03:00
comfyanonymous	f40076096e	Cleanup some lumina te code.	2025-02-25 04:10:26 -05:00
patientx	d705fe2e0b	Merge branch 'comfyanonymous:master' into master	2025-02-24 13:42:27 +03:00
comfyanonymous	96d891cb94	Speedup on some models by not upcasting bfloat16 to float32 on mac.	2025-02-24 05:41:32 -05:00
patientx	8142770e5f	Merge branch 'comfyanonymous:master' into master	2025-02-23 14:51:43 +03:00
comfyanonymous	ace899e71a	Prioritize fp16 compute when using allow_fp16_accumulation	2025-02-23 04:45:54 -05:00
patientx	c15fe75f7b	CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling `cublasLtMatmulAlgoGetHeuristic" ,error fix	2025-02-22 15:44:20 +03:00
patientx	26eb98b96f	Merge branch 'comfyanonymous:master' into master	2025-02-22 14:42:22 +03:00
comfyanonymous	aff16532d4	Remove some useless code.	2025-02-22 04:45:14 -05:00
comfyanonymous	072db3bea6	Assume the mac black image bug won't be fixed before v16.	2025-02-21 20:24:07 -05:00
comfyanonymous	a6deca6d9a	Latest mac still has the black image bug.	2025-02-21 20:14:30 -05:00
patientx	059397437b	Merge branch 'comfyanonymous:master' into master	2025-02-21 23:25:43 +03:00
comfyanonymous	41c30e92e7	Let all model memory be offloaded on nvidia.	2025-02-21 06:32:21 -05:00
patientx	603cacb14a	Merge branch 'comfyanonymous:master' into master	2025-02-20 23:06:56 +03:00
comfyanonymous	12da6ef581	Apparently directml supports fp16.	2025-02-20 09:30:24 -05:00
Silver	c5be423d6b	Fix link pointing to non-exisiting docs (#6891) ... * Fix link pointing to non-exisiting docs The current link is pointing to a path that does not exist any longer. I changed it to point to the currect correct path for custom nodes datatypes. * Update node_typing.py	2025-02-20 07:07:07 -05:00
patientx	a813e39d54	Merge branch 'comfyanonymous:master' into master	2025-02-19 16:19:26 +03:00
maedtb	5715be2ca9	Fix Hunyuan unet config detection for some models. (#6877) ... The change to support 32 channel hunyuan models is missing the `key_prefix` on the key. This addresses a complain in the comments of acc152b674.	2025-02-19 07:14:45 -05:00
patientx	4e6a5fc548	Merge branch 'comfyanonymous:master' into master	2025-02-19 13:52:34 +03:00
bymyself	afc85cdeb6	Add Load Image Output node (#6790) ... * add LoadImageOutput node * add route for input/output/temp files * update node_typing.py * use literal type for image_folder field * mark node as beta	2025-02-18 17:53:01 -05:00
Jukka Seppänen	acc152b674	Support loading and using SkyReels-V1-Hunyuan-I2V (#6862) ... * Support SkyReels-V1-Hunyuan-I2V * VAE scaling * Fix T2V oops * Proper latent scaling	2025-02-18 17:06:54 -05:00
patientx	3bde94efbb	Merge branch 'comfyanonymous:master' into master	2025-02-18 16:27:10 +03:00
comfyanonymous	b07258cef2	Fix typo. ... Let me know if this slows things down on 2000 series and below.	2025-02-18 07:28:33 -05:00
patientx	ef2e97356e	Merge branch 'comfyanonymous:master' into master	2025-02-17 14:04:15 +03:00
comfyanonymous	31e54b7052	Improve AMD arch detection.	2025-02-17 04:53:40 -05:00
comfyanonymous	8c0bae50c3	bf16 manual cast works on old AMD.	2025-02-17 04:42:40 -05:00
patientx	e8bf0ca27f	Merge branch 'comfyanonymous:master' into master	2025-02-17 12:42:02 +03:00
comfyanonymous	530412cb9d	Refactor torch version checks to be more future proof.	2025-02-17 04:36:45 -05:00
patientx	45c55f6cd0	Merge branch 'comfyanonymous:master' into master	2025-02-16 14:37:41 +03:00
comfyanonymous	e2919d38b4	Disable bf16 on AMD GPUs that don't support it.	2025-02-16 05:46:10 -05:00
patientx	6f05ace055	Merge branch 'comfyanonymous:master' into master	2025-02-14 13:50:23 +03:00
comfyanonymous	1cd6cd6080	Disable pytorch attention in VAE for AMD.	2025-02-14 05:42:14 -05:00
patientx	f125a37bdf	Update model_management.py	2025-02-14 12:33:27 +03:00
patientx	99d2824d5a	Update model_management.py	2025-02-14 12:30:19 +03:00
comfyanonymous	d7b4bf21a2	Auto enable mem efficient attention on gfx1100 on pytorch nightly 2.7 ... I'm not not sure which arches are supported yet. If you see improvements in memory usage while using --use-pytorch-cross-attention on your AMD GPU let me know and I will add it to the list.	2025-02-14 04:18:14 -05:00
patientx	4d66aa9709	Merge branch 'comfyanonymous:master' into master	2025-02-14 11:00:12 +03:00
comfyanonymous	019c7029ea	Add a way to set a different compute dtype for the model at runtime. ... Currently only works for diffusion models.	2025-02-13 20:34:03 -05:00
patientx	bce4176d3d	fixes to use pytorch-attention	2025-02-13 19:17:35 +03:00
patientx	f9ee02080f	Merge branch 'comfyanonymous:master' into master	2025-02-13 16:37:24 +03:00
comfyanonymous	8773ccf74d	Better memory estimation for ROCm that support mem efficient attention. ... There is no way to check if the card actually supports it so it assumes that it does if you use --use-pytorch-cross-attention with yours.	2025-02-13 08:32:36 -05:00
patientx	e4448cf48e	Merge branch 'comfyanonymous:master' into master	2025-02-12 15:50:23 +03:00
comfyanonymous	1d5d6586f3	Fix ruff.	2025-02-12 06:49:16 -05:00
zhoufan2956	35740259de	mix_ascend_bf16_infer_err (#6794)	2025-02-12 06:48:11 -05:00
comfyanonymous	ab888e1e0b	Add add_weight_wrapper function to model patcher. ... Functions can now easily be added to wrap/modify model weights.	2025-02-12 05:55:35 -05:00
comfyanonymous	d9f0fcdb0c	Cleanup.	2025-02-11 17:17:03 -05:00
HishamC	b124256817	Fix for running via DirectML (#6542) ... * Fix for running via DirectML Fix DirectML empty image generation issue with Flux1. add CPU fallback for unsupported path. Verified the model works on AMD GPUs * fix formating * update casual mask calculation	2025-02-11 17:11:32 -05:00
patientx	196fc385e1	Merge branch 'comfyanonymous:master' into master	2025-02-11 16:38:17 +03:00
comfyanonymous	af4b7c91be	Make --force-fp16 actually force the diffusion model to be fp16.	2025-02-11 08:33:09 -05:00
patientx	2a0bc66fed	Merge branch 'comfyanonymous:master' into master	2025-02-10 15:41:15 +03:00
comfyanonymous	4027466c80	Make lumina model work with any latent resolution.	2025-02-10 00:24:20 -05:00
patientx	9561b03cc7	Merge branch 'comfyanonymous:master' into master	2025-02-09 15:33:03 +03:00
comfyanonymous	095d867147	Remove useless function.	2025-02-09 07:02:57 -05:00
Pam	caeb27c3a5	res_multistep: Fix cfgpp and add ancestral samplers (#6731)	2025-02-08 19:39:58 -05:00
comfyanonymous	3d06e1c555	Make error more clear to user.	2025-02-08 18:57:24 -05:00
catboxanon	43a74c0de1	Allow FP16 accumulation with --fast (#6453) ... Currently only applies to PyTorch nightly releases. (>=20250208)	2025-02-08 17:00:56 -05:00
patientx	9a9da027b2	Merge branch 'comfyanonymous:master' into master	2025-02-07 12:02:36 +03:00
comfyanonymous	079eccc92a	Don't compress http response by default. ... Remove argument to disable it. Add new --enable-compress-response-body argument to enable it.	2025-02-07 03:29:21 -05:00
patientx	4a1e3ee925	Merge branch 'comfyanonymous:master' into master	2025-02-06 14:33:29 +03:00
comfyanonymous	14880e6dba	Remove some useless code.	2025-02-06 05:00:37 -05:00