comfyanonymous
8c4a9befa7
SD3 Support.
2024-06-10 14:06:23 -04:00
doctorpangloss
d778277a68
Merge with upstream and fix tests
2024-06-10 10:01:08 -07:00
comfyanonymous
a5e6a632f9
Support sampling non 2D latents.
2024-06-10 01:31:09 -04:00
comfyanonymous
742d5720d1
Support zeroing out text embeddings with the attention mask.
2024-06-09 16:51:58 -04:00
comfyanonymous
6cd8ffc465
Reshape the empty latent image to the right amount of channels if needed.
2024-06-08 02:35:08 -04:00
doctorpangloss
7f300bcb7a
Multi-modal LLM support and ongoing improvements to language features.
2024-06-07 16:23:10 -07:00
comfyanonymous
56333d4850
Use the end token for the text encoder attention mask.
2024-06-07 03:05:23 -04:00
doctorpangloss
6575409461
Additional chat templates to ease the use of many models.
2024-06-06 20:51:05 -07:00
doctorpangloss
ebf2ef27c7
Improve LLM / language support
2024-06-06 14:57:52 -07:00
comfyanonymous
104fcea0c8
Add function to get the list of currently loaded models.
2024-06-05 23:25:16 -04:00
comfyanonymous
b1fd26fe9e
pytorch xpu should be flash or mem efficient attention?
2024-06-04 17:44:14 -04:00
doctorpangloss
3f559135c6
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-06-03 11:42:55 -07:00
comfyanonymous
809cc85a8e
Remove useless code.
2024-06-02 19:23:37 -04:00
comfyanonymous
b249862080
Add an annoying print to a function I want to remove.
2024-06-01 12:47:31 -04:00
doctorpangloss
5151d5b017
Include HyperSD checkpoints
2024-05-31 16:21:10 -07:00
doctorpangloss
cb557c960b
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-31 07:42:11 -07:00
doctorpangloss
3125366eda
Improve compatibility with comfyui-extra-models, improve API
2024-05-30 16:50:34 -07:00
comfyanonymous
bf3e334d46
Disable non_blocking when --deterministic or directml.
2024-05-30 11:07:38 -04:00
JettHu
b26da2245f
Fix UnetParams annotation typo ( #3589 )
2024-05-27 19:30:35 -04:00
comfyanonymous
0920e0e5fe
Remove some unused imports.
2024-05-27 19:08:27 -04:00
comfyanonymous
ffc4b7c30e
Fix DORA strength.
...
This is a different version of #3298 with more correct behavior.
2024-05-25 02:50:11 -04:00
comfyanonymous
efa5a711b2
Reduce memory usage when applying DORA: #3557
2024-05-24 23:36:48 -04:00
doctorpangloss
801ef2e3f0
Fix interrupt messaging, add AMD and Intel Dockerfiles
2024-05-23 22:51:44 -07:00
doctorpangloss
a79ccd625f
bf16 selection for AMD
2024-05-22 22:45:15 -07:00
doctorpangloss
35cf996b68
ROCm 6.0 seems to require get_device_name to be called before memory methods in order to return valid data
2024-05-22 22:09:07 -07:00
comfyanonymous
6c23854f54
Fix OSX latent2rgb previews.
2024-05-22 13:56:28 -04:00
Chenlei Hu
7718ada4ed
Add type annotation UnetWrapperFunction ( #3531 )
...
* Add type annotation UnetWrapperFunction
* nit
* Add types.py
2024-05-22 02:07:27 -04:00
comfyanonymous
8508df2569
Work around black image bug on Mac 14.5 by forcing attention upcasting.
2024-05-21 16:56:33 -04:00
doctorpangloss
b241ecc56d
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-21 11:38:24 -07:00
comfyanonymous
83d969e397
Disable xformers when tracing model.
2024-05-21 13:55:49 -04:00
doctorpangloss
f69b6225c0
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-20 12:06:35 -07:00
comfyanonymous
1900e5119f
Fix potential issue.
2024-05-20 08:19:54 -04:00
comfyanonymous
09e069ae6c
Log the pytorch version.
2024-05-20 06:22:29 -04:00
comfyanonymous
11a2ad5110
Fix controlnet not upcasting on models that have it enabled.
2024-05-19 17:58:03 -04:00
comfyanonymous
0bdc2b15c7
Cleanup.
2024-05-18 10:11:44 -04:00
comfyanonymous
98f828fad9
Remove unnecessary code.
2024-05-18 09:36:44 -04:00
doctorpangloss
519cddcefc
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-17 14:04:44 -07:00
doctorpangloss
cb45b86b63
Patch torch device code here
2024-05-17 07:19:15 -07:00
doctorpangloss
4eb66f8a0a
Fix clip clone bug
2024-05-17 07:17:33 -07:00
comfyanonymous
19300655dd
Don't automatically switch to lowvram mode on GPUs with low memory.
2024-05-17 00:31:32 -04:00
doctorpangloss
87d1f30902
Some base nodes now have unit tests
2024-05-16 15:01:51 -07:00
doctorpangloss
3d98440fb7
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-16 14:28:49 -07:00
doctorpangloss
5a9055fe05
Tokenizers are now shallow cloned when CLIP is cloned. This allows nodes to add vocab to the tokenizer, as some checkpoints and LoRAs may require.
2024-05-16 12:39:19 -07:00
comfyanonymous
46daf0a9a7
Add debug options to force on and off attention upcasting.
2024-05-16 04:09:41 -04:00
comfyanonymous
2d41642716
Fix lowvram dora issue.
2024-05-15 02:47:40 -04:00
doctorpangloss
8741cb3ce8
LLM support in ComfyUI
...
- Currently uses `transformers`
- Supports model management and correctly loading and unloading models
based on what your machine can support
- Includes a Text Diffusers 2 workflow to demonstrate text rendering in
SD1.5
2024-05-14 17:30:23 -07:00
comfyanonymous
ec6f16adb6
Fix SAG.
2024-05-14 18:02:27 -04:00
comfyanonymous
bb4940d837
Only enable attention upcasting on models that actually need it.
2024-05-14 17:00:50 -04:00
comfyanonymous
b0ab31d06c
Refactor attention upcasting code part 1.
2024-05-14 12:47:31 -04:00
doctorpangloss
78e340e2d8
Traces now include the arguments for executing a node, wherever it makes sense to do so.
2024-05-13 15:48:16 -07:00
doctorpangloss
d11aed87ba
OpenAPI ImageRequestParameter node uses a Chrome user-agent to facilitate external URLs better
2024-05-13 15:03:34 -07:00
Simon Lui
f509c6fe21
Fix Intel GPU memory allocation accuracy and documentation update. ( #3459 )
...
* Change calculation of memory total to be more accurate, allocated is actually smaller than reserved.
* Update README.md install documentation for Intel GPUs.
2024-05-12 06:36:30 -04:00
comfyanonymous
fa6dd7e5bb
Fix lowvram issue with saving checkpoints.
...
The previous fix didn't cover the case where the model was loaded in
lowvram mode right before.
2024-05-12 06:13:45 -04:00
comfyanonymous
49c20cdc70
No longer necessary.
2024-05-12 05:34:43 -04:00
comfyanonymous
e1489ad257
Fix issue with lowvram mode breaking model saving.
2024-05-11 21:55:20 -04:00
doctorpangloss
188eff3376
Omit spurious traces
2024-05-09 17:11:40 -07:00
doctorpangloss
779ff30c17
Provide a protocol for plugins to declare model-management-manageable models. Docs will be updated to specify that plugin authors should use ModelPatcher generally.
2024-05-09 16:07:18 -07:00
doctorpangloss
c2fa74f625
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-09 13:45:38 -07:00
doctorpangloss
881258acb6
Progress bar hooks, via the server, are now set via a context. This will be used in other places too.
2024-05-09 13:24:06 -07:00
comfyanonymous
93e876a3be
Remove warnings that confuse people.
2024-05-09 05:29:42 -04:00
doctorpangloss
464c132c50
Add basic ImageRequestParameter node
2024-05-08 16:37:26 -07:00
doctorpangloss
0d8924442a
Improve API return values and tracing reports
2024-05-08 15:52:17 -07:00
comfyanonymous
cd07340d96
Typo fix.
2024-05-08 18:36:56 -04:00
doctorpangloss
aa0cfb54ce
Refine configuration of OpenTelemetry
2024-05-07 17:04:31 -07:00
doctorpangloss
3a64e04a93
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-07 13:57:53 -07:00
doctorpangloss
f8fcfa6f08
Improve tracing to propagate to backend workers correctly when using the API. Fix distributed tests.
2024-05-07 13:44:34 -07:00
comfyanonymous
c61eadf69a
Make the load checkpoint with config function call the regular one.
...
I was going to completely remove this function because it is unmaintainable
but I think this is the best compromise.
The clip skip and v_prediction parts of the configs should still work but
not the fp16 vs fp32.
2024-05-06 20:04:39 -04:00
doctorpangloss
75b63fce91
Remove redudant resume_download argument
2024-05-06 10:31:58 -07:00
doctorpangloss
eb7d466b95
Fix dependency on opentelemetry instrumentor; remove websocket based API example since it isn't appropriate for this fork.
2024-05-03 16:54:33 -07:00
doctorpangloss
fd81790f12
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-03 06:42:56 -07:00
doctorpangloss
330ecb10b2
Merge with upstream. Remove TLS flags, because a third party proxy will do this better
2024-05-02 21:57:20 -07:00
Simon Lui
a56d02efc7
Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. ( #3388 )
2024-05-02 03:26:50 -04:00
doctorpangloss
4d060f0555
Improve support for extra models
2024-05-01 16:58:29 -07:00
comfyanonymous
f81a6fade8
Fix some edge cases with samplers and arrays with a single sigma.
2024-05-01 17:05:30 -04:00
comfyanonymous
2aed53c4ac
Workaround xformers bug.
2024-04-30 21:23:40 -04:00
Garrett Sutula
bacce529fb
Add TLS Support ( #3312 )
...
* Add TLS Support
* Add to readme
* Add guidance for windows users on generating certificates
* Add guidance for windows users on generating certificates
* Fix typo
2024-04-30 20:17:02 -04:00
doctorpangloss
b94b90c1cc
Improve model downloader coherence with packages like controlnext-aux
2024-04-30 14:28:44 -07:00
doctorpangloss
0862863bc0
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-04-29 13:37:03 -07:00
doctorpangloss
46a712b4d6
Fix missing extension addition from upstream
2024-04-29 13:32:46 -07:00
Jedrzej Kosinski
7990ae18c1
Fix error when more cond masks passed in than batch size ( #3353 )
2024-04-26 12:51:12 -04:00
doctorpangloss
f965fb2bc0
Merge upstream
2024-04-24 22:41:43 -07:00
comfyanonymous
8dc19e40d1
Don't init a VAE model when there are no VAE weights.
2024-04-24 09:20:31 -04:00
comfyanonymous
c59fe9f254
Support VAE without quant_conv.
2024-04-18 21:05:33 -04:00
doctorpangloss
2643730acc
Tracing
2024-04-17 08:20:07 -07:00
comfyanonymous
719fb2c81d
Add basic PAG node.
2024-04-14 23:49:50 -04:00
comfyanonymous
258dbc06c3
Fix some memory related issues.
2024-04-14 12:08:58 -04:00
comfyanonymous
58812ab8ca
Support SDXS 512 model.
2024-04-12 22:12:35 -04:00
comfyanonymous
831511a1ee
Fix issue with sampling_settings persisting across models.
2024-04-09 23:20:43 -04:00
doctorpangloss
e49c662c7f
Enable previews by default and over distributed channels
2024-04-09 13:15:05 -07:00
doctorpangloss
37cca051b6
Enable real-time progress notifications.
2024-04-08 14:56:16 -07:00
doctorpangloss
dd6f7c4215
Fix retrieving history from distributed instance
2024-04-08 14:39:16 -07:00
doctorpangloss
034ffcea03
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-04-08 10:02:37 -07:00
comfyanonymous
30abc324c2
Support properly saving CosXL checkpoints.
2024-04-08 00:36:22 -04:00
comfyanonymous
0a03009808
Fix issue with controlnet models getting loaded multiple times.
2024-04-06 18:38:39 -04:00
kk-89
38ed2da2dd
Fix typo in lowvram patcher ( #3209 )
2024-04-05 12:02:13 -04:00
comfyanonymous
1088d1850f
Support for CosXL models.
2024-04-05 10:53:41 -04:00
doctorpangloss
3e002b9f72
Fix string joining node, improve model downloading
2024-04-04 23:40:29 -07:00
comfyanonymous
41ed7e85ea
Fix object_patches_backup not being the same object across clones.
2024-04-05 00:22:44 -04:00
comfyanonymous
0f5768e038
Fix missing arguments in cfg_function.
2024-04-04 23:38:57 -04:00
comfyanonymous
1f4fc9ea0c
Fix issue with get_model_object on patched model.
2024-04-04 23:01:02 -04:00