Commit Graph

3415 Commits

Author SHA1 Message Date
patientx
65855751b3
Merge branch 'comfyanonymous:master' into master 2025-01-15 09:19:24 +03:00
comfyanonymous
5b657f8c15 Allow setting start and end image in CosmosImageToVideoLatent. 2025-01-15 00:41:35 -05:00
patientx
104e6a9685
Merge branch 'comfyanonymous:master' into master 2025-01-15 03:59:33 +03:00
catboxanon
2cdbaf5169
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
c78a45685d
Rewrite res_multistep sampler and implement res_multistep_cfg_pp sampler. (#6462) 2025-01-14 18:20:06 -05:00
patientx
83db9e285d
Update README.md 2025-01-14 20:07:07 +03:00
patientx
4f01f72bed
Update zluda.py 2025-01-14 20:03:55 +03:00
patientx
c4861c74d4
UPDATED ZLUDA PATCHING METHOD 2025-01-14 19:57:22 +03:00
patientx
c3fc894ce2
Add files via upload 2025-01-14 19:54:44 +03:00
patientx
c7ebd121d6
Merge branch 'comfyanonymous:master' into master 2025-01-14 15:50:05 +03:00
comfyanonymous
3aaabb12d4 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
patientx
aa2a83ec35
Merge branch 'comfyanonymous:master' into master 2025-01-13 14:46:19 +03:00
comfyanonymous
1f1c7b7b56 Remove useless code. 2025-01-13 03:52:37 -05:00
patientx
b03621d13b
Merge branch 'comfyanonymous:master' into master 2025-01-12 14:31:19 +03:00
comfyanonymous
90f349f93d Add res_multistep sampler from the cosmos code.
This sampler should work with all models.
2025-01-12 03:10:07 -05:00
patientx
0b3d31e075
Merge branch 'comfyanonymous:master' into master 2025-01-12 03:34:57 +03:00
Alexander Piskun
b9d9bcba14
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
patientx
d557870f44
Add files via upload 2025-01-12 00:39:34 +03:00
patientx
d319705d78
Merge branch 'comfyanonymous:master' into master 2025-01-12 00:39:02 +03:00
patientx
bee349399f
patch any zluda into comfy 2025-01-12 00:38:51 +03:00
Chenlei Hu
42086af123
Merge ruff.toml into pyproject.toml (#6431) 2025-01-11 12:52:46 -05:00
Jedrzej Kosinski
6c9bd11fa3
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
patientx
8ac79a7563
Merge branch 'comfyanonymous:master' into master 2025-01-11 15:04:10 +03:00
comfyanonymous
ee8a7ab69d Fast latent preview for Cosmos. 2025-01-11 04:41:24 -05:00
patientx
d9d36d3155
Merge branch 'comfyanonymous:master' into master 2025-01-11 12:17:21 +03:00
Chenlei Hu
9c773a241b
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
adea2beb5c 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
patientx
8789f63df8
Update README.md 2025-01-11 02:44:40 +03:00
patientx
65b95a74fa
reverted zluda back to 3.8.4 2025-01-11 02:40:08 +03:00
patientx
cf086036af
reverted back to 3.8.4 2025-01-11 02:39:34 +03:00
patientx
51638c5e32
Update README.md 2025-01-11 00:37:28 +03:00
patientx
7a8103aa4b
Update install.bat 2025-01-11 00:30:55 +03:00
patientx
7d45042e2e
Merge branch 'comfyanonymous:master' into master 2025-01-10 18:31:48 +03:00
comfyanonymous
2ff3104f70 WIP support for Nvidia Cosmos 7B and 14B text to world (video) models. 2025-01-10 09:14:16 -05:00
patientx
00cf1206e8
Merge branch 'comfyanonymous:master' into master 2025-01-10 15:44:49 +03:00
comfyanonymous
129d8908f7 Add argument to skip the output reshaping in the attention functions. 2025-01-10 06:27:37 -05:00
patientx
c37b5ccf29
Merge branch 'comfyanonymous:master' into master 2025-01-09 18:15:43 +03:00
comfyanonymous
ff838657fa Cleaner handling of attention mask in ltxv model code. 2025-01-09 07:12:03 -05:00
patientx
0b933e1634
Merge branch 'comfyanonymous:master' into master 2025-01-09 12:57:31 +03:00
comfyanonymous
2307ff6746 Improve some logging messages. 2025-01-08 19:05:22 -05:00
patientx
867659b035
Merge branch 'comfyanonymous:master' into master 2025-01-08 01:49:22 +03:00
comfyanonymous
d0f3752e33 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
c515bdf371
fixed: robust loading comfy.settings.json (#6383)
https://github.com/comfyanonymous/ComfyUI/issues/6371
2025-01-07 16:03:56 -05:00
patientx
da70ccc210
Update README.md 2025-01-07 17:10:58 +03:00
patientx
09d53cb000
zluda update 2025-01-07 16:58:08 +03:00
patientx
08d62befa1
Update install.bat 2025-01-07 16:50:52 +03:00
patientx
0bc68eca52
updated zluda version to 3.8.5 2025-01-07 16:49:33 +03:00
patientx
6f553bdc19
Update fluxguide.md 2025-01-07 14:02:01 +03:00
patientx
e1aa83d068
Merge branch 'comfyanonymous:master' into master 2025-01-07 13:57:13 +03:00
comfyanonymous
4209edf48d Make a few more samplers deterministic. 2025-01-07 02:12:32 -05:00