ComfyUI-Dashscope

DashscopeEmoCaller

Detects a face in an input image, then submits the image and audio to Dashscope emotion video synthesis; its outputs are frames, frame count, video info, and audio.

Dashscope · 2 inputs · 0 parameters · 4 outputs

DashscopeLLMLoader

Selects a configured Dashscope LLM model version and returns it as a string.

Dashscope · 1 output

DashscopeModelCaller

Sends system and user prompts to a selected Dashscope model, optionally with an image, and returns response text. Without an image it uses text generation; with an image it uses multimodal conversation.

Dashscope · 1 input · 3 parameters · 1 output

DashscopeOCRCaller

Sends an image with configured pixel limits to a Dashscope multimodal model with an instruction to read its text, then returns response text.

Dashscope · 1 output

DashscopeVLMLoader

Selects a configured Dashscope VLM model version and returns it as a string.

Dashscope · 1 output