ComfyUI Node
Protoface LongCat Avatar 1.5 · Talking Avatar
LongCat Avatar 1.5 turns a portrait and speech audio into a talking-avatar video, with optional motion reference. Paid generation through your Protoface account. Keep generation_id fixed to reuse/resume; increment to generate again.
Protoface LongCat Avatar 1.5 · Talking Avatar
- video
- files
- run id
◄speech▾►
◄quality720p►
◄aspect_ratioauto►
◄person▾►
◄generation_id0►
◄request_scope►
CategoryProtoface/Video/meituan
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| speech | COMBO | Speech audio as a public URL, data URI, or asset id, no longer than 64 seconds. The API measures its duration automatically for pricing and video length. | |
| quality | COMBO | 720p | Output resolution tier. Upscaled tiers are identified in output_quality_descriptions. |
| aspect_ratio | COMBO | auto | Auto preserves the portrait framing; an explicit ratio center-crops the portrait before generation. |
| person | COMBO | A public URL, a data URI, or an asset id. | |
| generation_id | INT | 00–9007199254740991 | Keep fixed to reuse/resume this paid job. Increment for a fresh paid generation; independent of the model seed. |
| request_scope | STRING | Automatically assigned per node. Headless clients must supply a stable unique workflow/node ID. This is not a secret. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| files | PROTOFACE_FILE | — |
| run id | STRING | — |