ComfyUI Node
Pruna Video Avatar (Replicate)
A ComfyUI node in Replicate Select/lipsync with 14 inputs and 1 output.
Pruna Video Avatar (Replicate)
- image
- audio
- video_path
◄resolution720p►
◄voiceZephyr (Female)►
◄voice_script►
◄voice_promptSay the following.►
◄voice_languageEnglish (US)►
◄seed0►
◄video_promptThe person is talking.►
◄negative_prompt►
◄strength_negative_prompt0.50►
◄disable_safety_filtertrue►
◄disable_prompt_upsamplingfalse►
◄no_opfalse►
CategoryReplicate Select/lipsync
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | Input image (first frame). Supports jpg, jpeg, png, webp. | |
| resolutionopt | COMBO | 720p | Resolution of the video. |
| audioopt | AUDIO | Optional uploaded audio to drive avatar speech. If provided, this is used instead of voice_script and voice settings. | |
| voiceopt | COMBO | Zephyr (Female) | Voice to use when generating speech from voice_script. |
| voice_scriptopt | STRING | Exact words the avatar should say. Required when no audio file is uploaded. | |
| voice_promptopt | STRING | Say the following. | Optional style instructions for how to speak voice_script, such as tone, pacing, accent, or emotion. These instructions are not spoken. |
| voice_languageopt | COMBO | English (US) | Language/accent target for generated speech. |
| seedopt | INT | 0-2147483648–2147483647 | Random seed. Set for reproducible generation. |
| video_promptopt | STRING | The person is talking. | Optional visual prompt describing how the person should appear or behave while speaking. |
| negative_promptopt | STRING | Disabled if empty.Mention what you do NOT want in the video, e.g. "subtitles, text, blurry, low quality, frames, watermark, titles, scene change". We recommend using multiple keywords at once. | |
| strength_negative_promptopt | FLOAT | 0.500–4 | Strength of the Negative Prompt. Optimal value can differ for different video lengths (Experimental Feature) |
| disable_safety_filteropt | BOOLEAN | true | Disable safety filter for prompts and input image. When disabled, prompts are not checked for unsafe content before generation. |
| disable_prompt_upsamplingopt | BOOLEAN | false | When true, skip automatic enhancement of the visual video prompt and use video_prompt directly. |
| no_opopt | BOOLEAN | false | Health check mode - returns status without inference. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| video_path | STRING | — |