3041 Commits

Author SHA1 Message Date
comfyanonymous
89af33a700 Add minimum numpy version to requirements.txt 2025-01-15 20:19:56 -05:00
comfyanonymous
8527b20e98 CosmosImageToVideoLatent batch_size now does something. 2025-01-15 17:19:59 -05:00
comfyanonymous
12f925f2a2 Use latest python 3.12.8 the portable release. 2025-01-15 14:50:40 -05:00
comfyanonymous
fd4d654129 Remove unsafe embedding load for very old pytorch. 2025-01-15 04:32:23 -05:00
comfyanonymous
34cf225065 Force safe loading of files in torch format on pytorch 2.4+
If this breaks something for you make an issue.
2025-01-15 03:50:27 -05:00
comfyanonymous
b9e19b56e2 Allow setting start and end image in CosmosImageToVideoLatent. 2025-01-15 00:41:35 -05:00
catboxanon
ca8637c3f9 Add SetFirstSigma node (#6459)
Useful for models utilizing ztSNR. See: https://arxiv.org/abs/2409.15997
2025-01-14 19:05:45 -05:00
Pam
21ac610254 Rewrite res_multistep sampler and implement res_multistep_cfg_pp sampler. (#6462) 2025-01-14 18:20:06 -05:00
comfyanonymous
f19e3ec763 Implement Cosmos Image/Video to World (Video) diffusion models.
Use CosmosImageToVideoLatent to set the input image/video.
2025-01-14 05:14:10 -05:00
comfyanonymous
21a77abd0b Remove useless code. 2025-01-13 03:52:37 -05:00
comfyanonymous
302635bf4d Add res_multistep sampler from the cosmos code.
This sampler should work with all models.
2025-01-12 03:10:07 -05:00
Alexander Piskun
7d1a3db8d8 fixed a bug where a relative path was not converted to a full path (#6395)
Signed-off-by: bigcat88 <bigcat88@icloud.com>
2025-01-11 19:19:51 -05:00
Chenlei Hu
c55c2eb4f8 Merge ruff.toml into pyproject.toml (#6431) 2025-01-11 12:52:46 -05:00
Jedrzej Kosinski
ec567e2b7d Hooks Part 2 - TransformerOptionsHook and AdditionalModelsHook (#6377)
* Add 'sigmas' to transformer_options so that downstream code can know about the full scope of current sampling run, fix Hook Keyframes' guarantee_steps=1 inconsistent behavior with sampling split across different Sampling nodes/sampling runs by referencing 'sigmas'

* Cleaned up hooks.py, refactored Hook.should_register and add_hook_patches to use target_dict instead of target so that more information can be provided about the current execution environment if needed

* Refactor WrapperHook into TransformerOptionsHook, as there is no need to separate out Wrappers/Callbacks/Patches into different hook types (all affect transformer_options)

* Refactored HookGroup to also store a dictionary of hooks separated by hook_type, modified necessary code to no longer need to manually separate out hooks by hook_type

* In inner_sample, change "sigmas" to "sampler_sigmas" in transformer_options to not conflict with the "sigmas" that will overwrite "sigmas" in _calc_cond_batch

* Refactored 'registered' to be HookGroup instead of a list of Hooks, made AddModelsHook operational and compliant with should_register result, moved TransformerOptionsHook handling out of ModelPatcher.register_all_hook_patches, support patches in TransformerOptionsHook properly by casting any patches/wrappers/hooks to proper device at sample time

* Made hook clone code sane, made clear ObjectPatchHook and SetInjectionsHook are not yet operational

* Fix performance of hooks when hooks are appended via Cond Pair Set Props nodes by properly caching between positive and negative conds, make hook_patches_backup behave as intended (in the case that something pre-registers WeightHooks on the ModelPatcher instead of registering it at sample time)

* Filter only registered hooks on self.conds in CFGGuider.sample

* Make hook_scope functional for TransformerOptionsHook

* removed 4 whitespace lines to satisfy Ruff,

* Add a get_injections function to ModelPatcher

* Made TransformerOptionsHook contribute to registered hooks properly, added some doc strings and removed a so-far unused variable

* Rename AddModelsHooks to AdditionalModelsHook, rename SetInjectionsHook to InjectionsHook (not yet implemented, but at least getting the naming figured out)

* Clean up a typehint
2025-01-11 12:20:23 -05:00
comfyanonymous
e51102c5a8 Fast latent preview for Cosmos. 2025-01-11 04:41:24 -05:00
Chenlei Hu
63e5b7a9da Add pyproject.toml (#6386)
* Add pyproject.toml

* doc

* Static version file

* Add github action to sync version.py

* Change trigger to PR

* Fix commit

* Grant pr write permission

* nit

* nit

* Don't run on fork PRs

* Rename version.py to comfyui_version.py
2025-01-11 03:09:25 -05:00
comfyanonymous
97c5fc320a Add edm option to ModelSamplingContinuousEDM for Cosmos.
You can now use this node with "edm" selected to control the sigma_max and
sigma_min of the Cosmos model sampling.
2025-01-11 02:18:42 -05:00
comfyanonymous
6d9f172aeb WIP support for Nvidia Cosmos 7B and 14B text to world (video) models. 2025-01-10 09:14:16 -05:00
comfyanonymous
efae999351 Add argument to skip the output reshaping in the attention functions. 2025-01-10 06:27:37 -05:00
comfyanonymous
f57d3080b2 Cleaner handling of attention mask in ltxv model code. 2025-01-09 07:12:03 -05:00
comfyanonymous
095a9d32c7 Improve some logging messages. 2025-01-08 19:05:22 -05:00
comfyanonymous
6b210b9e9b Properly calculate inner dim for t5 model.
This is required to support some different types of t5 models.
2025-01-07 17:33:03 -05:00
Dr.Lt.Data
554e40887a fixed: robust loading comfy.settings.json (#6383)
https://github.com/comfyanonymous/ComfyUI/issues/6371
2025-01-07 16:03:56 -05:00
comfyanonymous
c75fa1bbf4 Make a few more samplers deterministic. 2025-01-07 02:12:32 -05:00
Chenlei Hu
d16e5c7194 Document get_attr and get_model_object (#6357)
* Document get_attr and get_model_object

* Update model_patcher.py

* Update model_patcher.py

* Update model_patcher.py
2025-01-06 20:12:22 -05:00
Chenlei Hu
dddbb48f0f Update frontend to v1.6.18 (#6368) 2025-01-06 18:42:45 -05:00
comfyanonymous
11fe0e25f3 Make ancestral samplers more deterministic. 2025-01-06 03:04:32 -05:00
Jedrzej Kosinski
7ccdd3112b In inner_sample, change "sigmas" to "sampler_sigmas" in transformer_options to not conflict with the "sigmas" that will overwrite "sigmas" in _calc_cond_batch (#6360) 2025-01-06 01:36:47 -05:00
Yoland Yan
47b577d450 Update CODEOWNERS (#6338)
Adding yoland and robin to web dir
2025-01-05 04:33:49 -05:00
Chenlei Hu
99a54da5bb Add update-frontend github action (#6336)
* Add update-frontend github action

* Update secrets

* nit
2025-01-05 04:32:11 -05:00
comfyanonymous
3c44819581 Make the device an optional parameter in the clip loaders. 2025-01-05 04:29:36 -05:00
comfyanonymous
c5357ca457 Add advanced device option to clip loader nodes.
Right click the "Load CLIP" or DualCLIPLoader node and "Show Advanced".
2025-01-05 01:46:11 -05:00
comfyanonymous
3e9956ca05 Remove old unused function. 2025-01-04 07:20:54 -05:00
Chenlei Hu
acaa111b5a Update web content to release v1.6.17 (#6337)
* Update web content to release v1.6.17

* Remove js maps
2025-01-03 16:22:08 -05:00
Chenlei Hu
57c26e2422 Update web content to release v1.6.16 (#6335)
* Update web content to release v1.6.16
2025-01-03 13:56:46 -05:00
comfyanonymous
5b622925eb Change defaults in nightly package workflow. 2025-01-03 12:12:17 -05:00
Chenlei Hu
93faf23afc Update web content to release v1.6.15 (#6324) 2025-01-02 19:20:48 -05:00
Terry Jia
1660cb5282 add fov and mask for load 3d node (#6308)
* add fov and mask for load 3d node

* some comments
2025-01-02 19:20:34 -05:00
Chenlei Hu
3635200b26 Update web content to release v1.6.14 (#6312) 2025-01-02 16:18:54 -05:00
comfyanonymous
7ce8ef2b20 Clear cache as often on AMD as Nvidia.
I think the issue this was working around has been solved.

If you notice that this change slows things down or causes stutters on
your AMD GPU with ROCm on Linux please report it.
2025-01-02 08:44:16 -05:00
Andrew Kvochko
c93c54d7d5 Fix temporal tiling for decoder, remove redundant tiles. (#6306)
This commit fixes the temporal tile size calculation, and removes
a redundant tile at the end of the range when its elements are
completely covered by the previous tile.

Co-authored-by: Andrew Kvochko <a.kvochko@lightricks.com>
2025-01-01 16:29:01 -05:00
comfyanonymous
884e96a8b8 Fix and enforce all ruff W rules. 2025-01-01 03:08:33 -05:00
blepping
1c63338e11 Fix unknown sampler error handling in calculate_sigmas function (#6280)
Modernize calculate_sigmas function
2024-12-31 17:33:50 -05:00
Jedrzej Kosinski
3720efe176 Add missing model_options param (#6296) 2024-12-31 14:46:55 -05:00
filtered
a7032e37dc Fix custom node type-hinting examples (#6281)
* Fix import in comfy_types doc / sample

* Clarify docstring
2024-12-31 03:41:09 -05:00
Alexander Piskun
b9ec5d7f94 fixed "verbose" argument (#6289)
Signed-off-by: bigcat88 <bigcat88@icloud.com>
2024-12-31 03:27:09 -05:00
comfyanonymous
014c90584e Fix and enforce no trailing whitespace. 2024-12-31 03:16:37 -05:00
blepping
b8ecee377b Add kl_optimal scheduler (#6206)
* Add kl_optimal scheduler

* Rename kl_optimal_schedule to kl_optimal_scheduler to be more consistent
2024-12-30 05:09:38 -05:00
comfyanonymous
6d49092554 Fix and enforce new lines at the end of files. 2024-12-30 04:14:59 -05:00
Jedrzej Kosinski
dfda2ed953 Add 'sigmas' to transformer_options so that downstream code can know about the full scope of current sampling run, fix Hook Keyframes' guarantee_steps=1 inconsistent behavior with sampling split across different Sampling nodes/sampling runs by referencing 'sigmas' (#6273) 2024-12-30 03:42:49 -05:00