* commit '2b7f9a8196304badb5fe58e5c734e4b182ad0fdf': (91 commits)
Fix the failing unit test. (#10037)
Make LatentCompositeMasked work with basic video latents. (#10023)
Fix memory leak by properly detaching model finalizer (#9979)
Fix issue with .view() in HuMo. (#10014)
Add new audio nodes (#9908)
Rodin3D - add [Rodin3D Gen-2 generate] api-node (#9994)
ComfyUI version 0.3.60
feat(api-nodes): add wan t2i, t2v, i2v nodes (#9996)
update template to 0.1.86 (#9998)
Fix bug with WanAnimateToVideo. (#9990)
Fix bug with WanAnimateToVideo node. (#9988)
add offset param (#9977)
Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. (#9986)
Set some wan nodes as no longer experimental. (#9976)
Lower wan memory estimation value a bit. (#9964)
Fix LoRA Trainer bugs with FP8 models. (#9854)
[Reviving #5709] Add strength input to Differential Diffusion (#9957)
Add inputs for character replacement to the WanAnimateToVideo node. (#9960)
Update WanAnimateToVideo to more easily extend videos. (#9959)
fix(seedream4): add flag to ignore error on partial success (#9952)
...
* Update default parameters for Moonvalley video nodes
- Changed default negative prompts to a more extensive list for both BaseMoonvalleyVideoNode and MoonvalleyVideo2VideoNode.
- Updated default guidance scale values for both nodes to enhance prompt adherence.
- Set a fixed default seed value for consistency in video generation.
* no message
* ruff fix
---------
Co-authored-by: thorsten <thorsten@tripod-digital.co.nz>
* [moonvalley] Update V2V node to match API specification
- Add exact resolution validation for supported resolutions (1920x1080, 1080x1920, 1152x1152, 1536x1152, 1152x1536)
- Change frame count validation from divisible by 32 to 16
- Add MP4 container format validation
- Remove internal parameters (steps, guidance_scale) from V2V inference params
- Update video duration handling to support only 5 seconds (auto-trim if longer)
- Add motion_intensity parameter (0-100) for Motion Transfer control type
- Add get_container_format() method to VideoInput classes
* update negative prompt
