* commit 'f4231a80b1b904b45ade0def9b37320c4adfe71b':
fix(Kling Image API Node): do not pass "image_type" when no image (#9271)
Support SimpleTuner lycoris lora for Qwen-Image (#9280)
Update template & embedded docs (#9283)
remove creation of non-used asyncio_loop (#9284)
Only show feature flags log when verbose. (#9281)
Bump pytorch cuda and rocm versions in readme instructions. (#9273)
Not sure if AMD actually support fp16 acc but it doesn't crash. (#9258)
Users report gfx1201 is buggy on flux with pytorch attention. (#9244)
async API nodes (#9129)
_ui.py import torchaudio safety check (#9234)
Fix RepeatLatentBatch not working on multi dim latents. (#9227)
Update frontend to v1.24.3 (#9175)
Update template to 0.1.52 (#9206)
Fixed an issue where qwenLora could not be loaded properly. (#9208)
- 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.
* [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
