ComfyUI Node
QWEN2_5_OMNI_Run
A ComfyUI node in Qwen2_5-Omni with 11 inputs and 2 outputs.
QWEN2_5_OMNI_Run
- QWEN2_5_OMNI_model
- image
- video
- audio
- BatchImage
- text
- audio
◄text►
◄video_decode_methodtorchvision►
◄use_audio_in_videotrue►
◄return_audiotrue►
◄Voice_TypeChelsie►
◄seed1►
CategoryQwen2_5-Omni
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | — | |
| QWEN2_5_OMNI_model | QWEN2_5_OMNI_MODEL | — | |
| video_decode_method | COMBO | torchvision | 3 options: torchvision, decord, torchcodec |
| use_audio_in_video | BOOLEAN | true | — |
| return_audio | BOOLEAN | true | The model can batch inputs composed of mixed samples of various types such as text, images, audio and videos as input when return_audio=False is set.当设置 return_audio=False 时，该模型可以将由各种类型的混合样本（如文本、图像、音频和视频）组成的 Importing 进行批处理作为输入。In order to obtain a flexible experience, we recommend that users can decide whether to return audio when generate function is called. If return_audio is set to False, the model will only return text outputs to get text responses faster.为了获得灵活的体验，我们建议用户可以决定在调用 generate 函数时是否返回音频。如果 return_audio 设置为 False，则模型将仅返回文本输出以更快地获得文本响应。 |
| Voice_Type | COMBO | Chelsie | Chelsie:Female, A honeyed, velvety voice that carries a gentle warmth and luminous clarity.甜美、天鹅绒般的嗓音，带着温柔的温暖和明亮的清晰度。Ethan:Male, A bright, upbeat voice with infectious energy and a warm, approachable vibe.明亮、乐观的声音，具有感染力和温暖、平易近人的氛围。 |
| seed | INT | 11–18446744073709550000 | — |
| imageopt | IMAGE | — | |
| videoopt | VIDEO | — | |
| audioopt | AUDIO | — | |
| BatchImageopt | BatchImage | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| audio | AUDIO | — |