Commit Graph

33 Commits

Author SHA1 Message Date
doctorpangloss
e7d0cc457d fix tests, replace broken llava and fix transformers videos issue 2025-12-11 14:23:05 -08:00
doctorpangloss
9c892a9b34 pass unit tests 2025-12-09 16:13:43 -08:00
doctorpangloss
7fb748fcef wip merge 2025-12-09 13:22:27 -08:00
doctorpangloss
b149031748 add video support for language models, improve torch compile for transformers models, make it easier to load videos, fix progess messages from language nodes 2025-12-03 14:40:27 -08:00
doctorpangloss
97f911280e Improve lazy graph evaluation, add logic operators 2025-10-31 14:27:27 -07:00
Benjamin Berman
82bffb7855 Better integration with logic nodes from EasyUse
- ImageRequestParameter now returns None or a provided default when the value of its path / URL is empty, instead of erroring
 - Custom nodes which touch nodes.NODE_CLASS_MAPPINGS will once again see all the nodes available during execution, instead of only the base nodes
2025-10-29 15:36:35 -07:00
doctorpangloss
c48163e78c Fix misalignment between EXIF tags and whatever pillow was actually doing 2025-09-19 16:14:40 -07:00
doctorpangloss
e6762bb82a Use pylint dynamic member correctly 2025-09-18 13:42:05 -07:00
doctorpangloss
79b8723f61 Various fixes
- Fix 16 bit exif saving for PNGs
 - Validate alternative filenames correctly
 - Improve speed of test workflows by setting steps to 1
2025-09-17 16:04:05 -07:00
doctorpangloss
3d23c298a2 Fix JPEG WebP and TIFF EXIF 2025-09-17 12:18:15 -07:00
doctorpangloss
a464dfa3db fix issue when trying to write to a file that already exists 2025-07-11 13:52:15 -07:00
doctorpangloss
2528a76a05 Fix pylint issues 2025-02-24 09:06:03 -08:00
doctorpangloss
fb4ea2dc6d 16 bit color support for TIFF and PNG, 16 and 32 bit floating point
support in EXR
2025-02-21 17:55:02 -08:00
doctorpangloss
42f75cadc0 Generators 2025-02-20 15:00:07 -08:00
doctorpangloss
9e8bb0b297 Add image tracing to SVG support using vtrace, python skia. The Skia library can be used for additional drawing tasks 2024-08-28 14:49:19 -07:00
doctorpangloss
3e54f9da36 Fix torch_dtype issues, missing DualCLIPLoader known model support 2024-08-20 23:00:12 -07:00
doctorpangloss
f1a096b3e1 Merges new frontend
- fixes bfloat16 on cpu to numpy issues
 - extensions should go into comfy/web/extensions/javascript
2024-08-16 15:46:11 -07:00
doctorpangloss
7500d02af5 Improve language models and performance, adding a translation workflow example 2024-08-15 11:09:55 -07:00
doctorpangloss
0549f35e85 Merge commit '39fb74c5bd13a1dccf4d7293a2f7a755d9f43cbd' of github.com:comfyanonymous/ComfyUI
- Improvements to tests
 - Fixes model management
 - Fixes issues with language nodes
2024-08-13 20:08:56 -07:00
Benjamin Berman
d1ad0407db Fix incorrect declaration of exif nodes required versus optional fields 2024-08-02 18:45:28 -07:00
doctorpangloss
3d67224937 Improve model downloading from Hugging Face Hub 2024-07-09 12:57:33 -07:00
doombubbles
0ab8c4f228 Update SaveImagesResponse 2024-07-04 12:17:32 -07:00
doctorpangloss
ef38598030 Fix validation issues 2024-06-18 20:25:57 -07:00
doctorpangloss
7f300bcb7a Multi-modal LLM support and ongoing improvements to language features. 2024-06-07 16:23:10 -07:00
doctorpangloss
3125366eda Improve compatibility with comfyui-extra-models, improve API 2024-05-30 16:50:34 -07:00
doctorpangloss
8a3b49eb49 Resolves SSL errors on Windows when using fsspec 2024-05-29 17:42:15 -07:00
doctorpangloss
355f2aef3a Fix parameters and user agent for ImageRequestParameter. 2024-05-13 17:59:02 -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
doctorpangloss
464c132c50 Add basic ImageRequestParameter node 2024-05-08 16:37:26 -07:00
doctorpangloss
3e002b9f72 Fix string joining node, improve model downloading 2024-04-04 23:40:29 -07:00
doctorpangloss
b0be335d59 Improved support for ControlNet workflows with depth
- ComfyUI can now load EXR files.
 - There are new arithmetic nodes for floats and integers.
 - EXR nodes can load depth maps and be remapped with
   ImageApplyColormap. This allows end users to use ground truth depth
   data from video game engines or 3D graphics tools and recolor it to
   the format expected by depth ControlNets: grayscale inverse depth
   maps and "inferno" colored inverse depth maps.
 - Fixed license notes.
 - Added an additional known ControlNet model.
 - Because CV2 is now used to read OpenEXR files, an environment
   variable must be set early on in the application, before CV2 is
   imported. This file, main_pre, is now imported early on in more
   places.
2024-03-26 22:32:15 -07:00
doctorpangloss
d8846fcb39 Improved testing of API nodes
- dynamicPrompts now set to False by default; CLIPTextEncoder and
   related nodes now have it set to True.
 - Fixed return values of API nodes.
2024-03-22 22:04:35 -07:00
doctorpangloss
feae8c679b Add nodes to support OpenAPI and similar backend workflows 2024-03-22 14:22:50 -07:00