Seedance 2.0 Mini: Text to Video is a minimal, focused ComfyUI workflow that turns a plain-language prompt into a finished video in one pass. It centers on a single generation node—ByteDance2TextToVideoNode—to call Dreamina’s Seedance 2.0 Mini API, and a SaveVideo node to write the result to disk. Because generation happens via API, your local machine mainly handles orchestration and saving, not heavy rendering. The node accepts your text prompt and key generation settings (such as duration, aspect ratio/resolution, FPS, and seed) and returns a ready-to-save clip.

Technically, the ByteDance2TextToVideoNode encapsulates model inference: it submits your prompt and parameters to Seedance 2.0 Mini, which handles motion, subject fidelity, and scene composition. The model supports AI camera behavior (e.g., dolly, pan, orbit-like motion) through prompt cues and/or any dedicated camera fields exposed by the node. For character continuity across multiple shots, keep a stable character description and reuse the same seed between runs. The downstream SaveVideo node then encodes the returned video stream to a file format supported by your ComfyUI/FFmpeg setup, typically MP4 or WebM.