Commit Graph

1533 Commits

Author SHA1 Message Date
patientx
3402d28bcd
Merge branch 'comfyanonymous:master' into master 2025-01-21 00:06:28 +03:00
comfyanonymous
fb2ad645a3 Add FluxDisableGuidance node to disable using the guidance embed. 2025-01-20 14:50:24 -05:00
patientx
39e164a441
Merge branch 'comfyanonymous:master' into master 2025-01-20 19:27:59 +03:00
comfyanonymous
d8a7a32779 Cleanup old TODO. 2025-01-20 03:44:13 -05:00
patientx
df418fc3fd
added rocm and hip hiding for certain nodes getting errors under zluda 2025-01-19 17:49:55 +03:00
patientx
88eae2b0d1
Merge branch 'comfyanonymous:master' into master 2025-01-19 15:11:53 +03:00
Sergii Dymchenko
ebf038d4fa
Use torch.special.expm1 (#6388)
* Use `torch.special.expm1`

This function provides greater precision than `exp(x) - 1` for small values of `x`.

Found with TorchFix https://github.com/pytorch-labs/torchfix/

* Use non-alias
2025-01-19 04:54:32 -05:00
patientx
8ee302c9dd
Merge branch 'comfyanonymous:master' into master 2025-01-19 02:40:53 +03:00
catboxanon
b1a02131c9
Remove comfy.samplers self-import (#6506) 2025-01-18 17:49:51 -05:00
patientx
e3207a0560
Merge branch 'comfyanonymous:master' into master 2025-01-18 16:08:27 +03:00
comfyanonymous
507199d9a8 Uni pc sampler now works with audio and video models. 2025-01-18 05:27:58 -05:00
comfyanonymous
2f3ab40b62 Add warning when using old pytorch versions. 2025-01-17 18:47:27 -05:00
patientx
5388be0f56
Merge branch 'comfyanonymous:master' into master 2025-01-17 09:41:17 +03:00
comfyanonymous
0aa2368e46 Fix some cosmos fp8 issues. 2025-01-16 17:45:37 -05:00
comfyanonymous
cca96a85ae Fix cosmos VAE failing with videos longer than 121 frames. 2025-01-16 16:30:06 -05:00
patientx
4afa79a368
Merge branch 'comfyanonymous:master' into master 2025-01-16 17:23:00 +03:00
comfyanonymous
31831e6ef1 Code refactor. 2025-01-16 07:23:54 -05:00
comfyanonymous
88ceb28e20 Tweak hunyuan memory usage factor. 2025-01-16 06:31:03 -05:00
patientx
ed13b68e4f
Merge branch 'comfyanonymous:master' into master 2025-01-16 13:59:32 +03:00
comfyanonymous
23289a6a5c Clean up some debug lines. 2025-01-16 04:24:39 -05:00
comfyanonymous
9d8b6c1f46 More accurate memory estimation for cosmos and hunyuan video. 2025-01-16 03:48:40 -05:00
patientx
a779e34c5b
Merge branch 'comfyanonymous:master' into master 2025-01-16 11:29:26 +03:00
comfyanonymous
6320d05696 Slightly lower hunyuan video memory usage. 2025-01-16 00:23:01 -05:00
comfyanonymous
25683b5b02 Lower cosmos diffusion model memory usage. 2025-01-15 23:46:42 -05:00
comfyanonymous
4758fb64b9 Lower cosmos VAE memory usage by a bit. 2025-01-15 22:57:52 -05:00
comfyanonymous
008761166f Optimize first attention block in cosmos VAE. 2025-01-15 21:48:46 -05:00
patientx
fb0d92b160
Merge branch 'comfyanonymous:master' into master 2025-01-15 23:33:05 +03:00
comfyanonymous
cba58fff0b Remove unsafe embedding load for very old pytorch. 2025-01-15 04:32:23 -05:00
patientx
3ece3091d4
Merge branch 'comfyanonymous:master' into master 2025-01-15 11:55:19 +03:00
comfyanonymous
2feb8d0b77 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
patientx
104e6a9685
Merge branch 'comfyanonymous:master' into master 2025-01-15 03:59:33 +03:00
Pam
c78a45685d
Rewrite res_multistep sampler and implement res_multistep_cfg_pp sampler. (#6462) 2025-01-14 18:20:06 -05:00
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
d319705d78
Merge branch 'comfyanonymous:master' into master 2025-01-12 00:39:02 +03:00
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
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