1964 Commits (25a4805e519ea97110651ae5bb1d7c0e6644b26f)
 

Author SHA1 Message Date
comfyanonymous 04b713dda1 Fix VALIDATE_INPUTS getting called multiple times.
Allow VALIDATE_INPUTS to only validate specific inputs.
1 year ago
comfyanonymous 12e822c6c8 Use function to calculate model size in model patcher. 1 year ago
comfyanonymous e1e322cf69 Load weights that can't be lowvramed to target device. 1 year ago
comfyanonymous a8baa40d85 Cleanup. 1 year ago
comfyanonymous c782144433 Fix clip vision lowvram mode not working. 1 year ago
comfyanonymous e478b1794e Only add _meta title to api prompt when dev mode is enabled in UI. 1 year ago
AYF f15dce71fd
Add title to the API workflow json. (#2380)
* Add `title` to the API workflow json.

* API: Move `title` to `_meta` dictionary, imply unused.
1 year ago
comfyanonymous f21bb41787 Fix taesd VAE in lowvram mode. 1 year ago
comfyanonymous 61b3f15f8f Fix lowvram mode not working with unCLIP and Revision code. 1 year ago
shiimizu 392878a262 Fix hiding dom widgets. 1 year ago
comfyanonymous 257c2eaaa4 Merge branch 'patch-1' of https://github.com/savolla/ComfyUI 1 year ago
comfyanonymous d0165d819a Fix SVD lowvram mode. 1 year ago
comfyanonymous a252963f95 --disable-smart-memory now unloads everything like it did originally. 1 year ago
comfyanonymous 36a7953142 Greatly improve lowvram sampling speed by getting rid of accelerate.
Let me know if this breaks anything.
1 year ago
comfyanonymous 261bcbb0d9 A few missing comfy ops in the VAE. 1 year ago
comfyanonymous d35267e85a Litegraph updates.
Update from upstream repo.

Auto select value in prompt.

Increase maximum number of nodes to 10k.
1 year ago
comfyanonymous 6781b181ef Fix potential tensor device issue with ImageCompositeMasked. 1 year ago
comfyanonymous a1e1c69f7d LoadImage now loads all the frames from animated images as a batch. 1 year ago
comfyanonymous 5f54614e7f Add a RebatchImages node. 1 year ago
comfyanonymous e82942cc29 Add a denoise parameter to the SDTurboScheduler. 1 year ago
comfyanonymous ba3f3aa1ca Merge branch 'test-reliability' of https://github.com/pythongosssss/ComfyUI 1 year ago
pythongosssss 8680ac3dfd try to improve test reliability 1 year ago
pythongosssss e65110fd93 Fix dom widgets not being hidden 1 year ago
Oleksiy Nehlyadyuk 40ea2bd011
Update requirements.txt
the UI launches with one missing module `torchvision`. spits out a `ModuleNotFoundError`. installing `torchvision` module fixed it.
1 year ago
comfyanonymous 9a7619b72d Fix regression with inpaint model. 1 year ago
comfyanonymous 571ea8cdcc Fix SAG not working with cfg 1.0 1 year ago
comfyanonymous 8cf1daa108 Fix SDXL area composition sometimes not using the right pooled output. 1 year ago
comfyanonymous d2f322902c Fix wrong Stable Zero123 node name. 1 year ago
comfyanonymous 2258f85159 Support stable zero 123 model.
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
1 year ago
comfyanonymous 2f9d6a97ec Add --deterministic option to make pytorch use deterministic algorithms. 1 year ago
comfyanonymous a036b94075 Move SaveAnimated nodes to image->animation. 1 year ago
pythongosssss 6453dc1ca2 Fix name counter preventing more than 3 of the same node
Fix linked widget offset when populating values
1 year ago
comfyanonymous e45d920ae3 Don't resize clip vision image when the size is already good. 1 year ago
comfyanonymous 13e6d5366e Switch clip vision to manual cast.
Make it use the same dtype as the text encoder.
1 year ago
comfyanonymous 574efd3782 Fix perpneg not working on SDXL. 1 year ago
comfyanonymous 172984db01 Fix SAG not working on certain resolutions. 1 year ago
comfyanonymous 6596654d47 Add a LatentBatch node. 1 year ago
comfyanonymous 719fa0866f Set clip vision model in eval mode so it works without inference mode. 1 year ago
comfyanonymous adc40e3d7b Forgot this. 1 year ago
comfyanonymous 014c8bf2f2 Refactor LCM to support more model types. 1 year ago
comfyanonymous 9cad2f06ff Make perp neg take a conditioning input instead of a CLIP one. 1 year ago
Hari 574363a8a6 Implement Perp-Neg 1 year ago
comfyanonymous a5056cfb1f Remove useless code. 1 year ago
comfyanonymous b12b48e170 cleanup. 1 year ago
comfyanonymous 329c571993 Improve code legibility. 1 year ago
comfyanonymous 6c5990f7db Fix cfg being calculated more than once if sampler_cfg_function. 1 year ago
comfyanonymous ba04a87d10 Refactor and improve the sag node.
Moved all the sag related code to comfy_extras/nodes_sag.py
1 year ago
Rafie Walker 6761233e9d
Implement Self-Attention Guidance (#2201)
* First SAG test

* need to put extra options on the model instead of patcher

* no errors and results seem not-broken

* Use @ashen-uncensored formula, which works better!!!

* Fix a crash when using weird resolutions. Remove an unnecessary UNet call

* Improve comments, optimize memory in blur routine

* SAG works with sampler_cfg_function
1 year ago
pythongosssss 390078904c
Group node fixes (#2259)
* Prevent cleaning graph state on undo/redo

* Remove pause rendering due to LG bug

* Fix crash on disconnected internal reroutes

* Fix widget inputs being incorrect order and value

* Fix initial primitive values on connect

* basic support for basic rerouted converted inputs

* Populate primitive to reroute input

* dont crash on bad primitive links

* Fix convert to group changing control value

* reduce restrictions

* fix random crash in tests
1 year ago
comfyanonymous b454a67bb9 Support segmind vega model. 1 year ago