Christian Byrne
d8d215dd3a
Use common download function in kling nodes module ( #67 )
2025-04-30 10:39:46 -07:00
Christian Byrne
021e64db6c
Fix: PollingOperation progress bar update progress by absolute value ( #65 )
2025-04-30 09:09:27 -07:00
Christian Byrne
1bae2de0d8
Add types and doctstrings to utils file ( #64 )
2025-04-30 08:56:32 -07:00
thot experiment
f7c70b3822
split remaining nodes out of nodes_api, make utility lib, refactor ideogram ( #61 )
2025-04-30 08:35:01 -07:00
Jedrzej Kosinski
9db268849d
Added Recraft Controls + Recraft Color RGB nodes ( #57 )
2025-04-30 05:51:14 -05:00
Jedrzej Kosinski
814c86d8d4
Added pixverse_template support to Pixverse Text to Video node ( #54 )
2025-04-30 04:31:37 -05:00
Jedrzej Kosinski
48a0ef6311
Add Recraft Text to Vector node, add Save SVG node to handle its output ( #53 )
2025-04-30 03:55:49 -05:00
Jedrzej Kosinski
a90dd38634
Add Minimax Image to Video node + Cleanup ( #51 )
2025-04-30 02:59:27 -05:00
Jedrzej Kosinski
31a33a5387
Move and edit Minimax node to nodes_minimax.py ( #50 )
2025-04-30 01:51:57 -05:00
Jedrzej Kosinski
b121fac8a4
Move and fix BFL nodes to node_bfl.py ( #49 )
2025-04-30 01:22:32 -05:00
Jedrzej Kosinski
f73c702829
Add Pixverse nodes ( #46 )
2025-04-30 01:03:04 -05:00
Jedrzej Kosinski
75611aa449
Moved Recraft nodes to nodes_recraft.py ( #48 )
2025-04-30 00:37:54 -05:00
Jedrzej Kosinski
48a07964e3
Moved Luma nodes to nodes_luma.py ( #47 )
2025-04-30 00:20:31 -05:00
Christian Byrne
c42295c579
Fix image upload for Luma: only include Content-Type header field if it's set explicitly ( #40 )
2025-04-29 20:31:09 -05:00
Christian Byrne
2d4d2f0dfe
Fix runway image upload and progress polling ( #39 )
2025-04-29 18:05:00 -07:00
comfyanonymous
dbc726f80c
Better vace memory estimation. ( #7875 )
2025-04-29 20:42:00 -04:00
comfyanonymous
7ee96455e2
Bump minimum pyav version to 14.2.0 ( #7874 )
2025-04-29 20:38:45 -04:00
Jedrzej Kosinski
d10a1259fa
Add Realistic Image and Logo Raster styles for Recraft v3 ( #38 )
2025-04-29 19:30:45 -05:00
comfyanonymous
0a66d4b0af
Per device stream counters for async offload. ( #7873 )
2025-04-29 20:28:52 -04:00
thot experiment
122a4b4288
add better error propagation to veo2 ( #37 )
2025-04-29 17:28:18 -07:00
Christian Byrne
cc9ce9ad9b
Set Content-Type header when uploading files ( #36 )
2025-04-29 16:15:50 -07:00
Christian Byrne
fb78ec1477
Standard CATEGORY system for api nodes ( #35 )
2025-04-29 15:32:44 -07:00
Christian Byrne
ce7d007872
Convert Minimax node to use VIDEO output type ( #34 )
2025-04-29 14:40:42 -07:00
Christian Byrne
520d5f996b
Add Runway nodes ( #17 )
2025-04-29 14:02:21 -07:00
Jedrzej Kosinski
557328a9ee
Add Camera Concepts (luma_concepts) to Luma Video nodes ( #33 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-04-29 15:50:09 -05:00
Christian Byrne
4a67cdb23a
Add Kling Nodes ( #12 )
2025-04-29 12:44:23 -07:00
Jedrzej Kosinski
e92f6e1c72
Add Recraft nodes ( #29 )
2025-04-29 14:33:00 -05:00
thot experiment
850f5daff6
add veo2, bump av req ( #32 )
2025-04-29 12:25:41 -07:00
Christian Byrne
acbf26c7d1
Add utils to map from pydantic model fields to comfy node inputs ( #30 )
2025-04-29 11:53:10 -07:00
Chenlei Hu
9c7e9d8836
[Bug] Remove duplicated option T2V-01 in MinimaxTextToVideoNode ( #31 )
2025-04-29 14:31:02 -04:00
Terry Jia
5c5457a4ef
support more example folders ( #7836 )
...
* support more example folders
* add warning message
2025-04-29 11:28:04 -04:00
Chenlei Hu
45503f6499
Add release process section to README ( #7855 )
...
* Add release process section to README
* move
* Update README.md
2025-04-29 06:32:34 -04:00
comfyanonymous
005a91ce2b
Latest desktop and portable should work on blackwell. ( #7861 )
...
Removed the mention about the cards from the readme.
2025-04-29 06:29:38 -04:00
guill
68f0d35296
Add support for VIDEO as a built-in type ( #7844 )
...
* Add basic support for videos as types
This PR adds support for VIDEO as first-class types. In order to avoid
unnecessary costs, VIDEO outputs must implement the `VideoInput` ABC,
but their implementation details can vary. Included are two
implementations of this type which can be returned by other nodes:
* `VideoFromFile` - Created with either a path on disk (as a string) or
a `io.BytesIO` containing the contents of a file in a supported format
(like .mp4). This implementation won't actually load the video unless
necessary. It will also avoid re-encoding when saving if possible.
* `VideoFromComponents` - Created from an image tensor and an optional
audio tensor.
Currently, only h264 encoded videos in .mp4 containers are supported for
saving, but the plan is to add additional encodings/containers in the
near future (particularly .webm).
* Add optimization to avoid parsing entire video
* Improve type declarations to reduce warnings
* Make sure bytesIO objects can be read many times
* Fix a potential issue when saving long videos
* Fix incorrect type annotation
* Add a `LoadVideo` node to make testing easier
* Refactor new types out of the base comfy folder
I've created a new `comfy_api` top-level module. The intention is that
anything within this folder would be covered by semver-style versioning
that would allow custom nodes to rely on them not introducing breaking
changes.
* Fix linting issue
2025-04-29 05:58:00 -04:00
Jedrzej Kosinski
577423b65f
Fix image_luma_ref not working ( #28 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-04-29 02:18:13 -05:00
Jedrzej Kosinski
1c15da7026
Add rest of Luma node functionality ( #19 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-04-29 01:43:14 -05:00
guill
4f8b235fda
Add VIDEO type ( #21 )
2025-04-28 22:11:32 -07:00
Christian Byrne
e9fa0616fd
Refactor util functions ( #20 )
2025-04-28 21:52:45 -07:00
Jedrzej Kosinski
f8f2f3c5fb
Add Luma nodes ( #16 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-04-28 22:54:35 -05:00
Robin Huang
2018a0d523
Add function for uploading files. ( #18 )
2025-04-28 17:01:25 -07:00
Christian Byrne
442dc70c07
Manually add BFL polling status response schema ( #15 )
2025-04-28 17:17:57 -05:00
thot-experiment
66d42afd23
remove validation to make it easier to run against LAN copies of the API
2025-04-28 15:01:16 -07:00
Robin Huang
019ec67e1d
Add instructions for staging development. ( #14 )
2025-04-28 13:29:45 -07:00
Chenlei Hu
864d0f7395
Add --comfy-api-base launch arg ( #13 )
2025-04-28 15:07:49 -04:00
comfyanonymous
83d04717b6
Support HiDream E1 model. ( #7857 )
2025-04-28 15:01:15 -04:00
Jedrzej Kosinski
788bc2f6b4
Added initial BFL Flux 1.1 [pro] Ultra node ( #11 )
2025-04-28 13:54:40 -05:00
Yoland Yan
7d329771f9
Add moderation level option to OpenAIGPTImage1 node and update api_call method signature ( #7804 )
2025-04-28 13:59:22 -04:00
chaObserv
c15909bb62
CFG++ for gradient estimation sampler ( #7809 )
2025-04-28 13:51:35 -04:00
Andrew Kvochko
772b4c5945
ltxv: overwrite existing mask on conditioned frame. ( #7845 )
...
This commit overwrites the noise mask on the latent frame that is being
conditioned with keyframe conditioning, setting it to one.
2025-04-28 13:42:04 -04:00
comfyanonymous
5a50c3c7e5
Fix stream priority to support older pytorch. ( #7856 )
2025-04-28 13:07:21 -04:00
