Seedance 2.0 Mini: Text to Video

Generate cinematic videos from text prompts with Dreamina’s Seedance 2.0 Mini, supporting AI camera controls and consistent character generation across scenes. This workflow takes only prompt input and produces 1 video output. Ideal for AI filmmaking, branded content creation, and multi-shot storytelling projects.

Download Workflow Try in Cloud

About

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.

What you provide

Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud

Output

Example

Sample output

Use this workflow from code

Generated from the workflow graph and inputs when possible; stored examples are shown otherwise. Review credentials and endpoints before running code, which may incur charges.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "1": {
        "class_type": "ByteDance2TextToVideoNode",
        "inputs": {
            "model": "Seedance 2.0 Mini",
            "model.duration": 5,
            "model.generate_audio": True,
            "model.prompt": "[Style] Photorealistic futuristic space warfare, 8K, blockbuster fleet battle, cold silver hulls, rim-lit by a gas giant below.\n\n[Duration] ~5 seconds.\n\n[Scene] Low orbit above a massive ringed gas giant. A kilometer-scale carrier hangs in frame, launch bays glowing. Six small interceptors pour out in formation.\n\nShot 1: Slow crane down from the carrier's hull. Interceptors accelerate outward in a tight V-formation, exhaust trails curling against the planet's cloud bands.\n\nShot 2: Cut to medium chase shot behind the lead interceptor. It pitches up slightly, weaving through drifting orbital debris shields—movements smooth and controlled, not violent.\n\nShot 3: Wide static hold, then gentle push-in. The swarm spreads into attack spread as a distant enemy silhouette flickers on the horizon—one brief red warning glint on a HUD reflection in the canopy.\n\nConstraints: stable proportions, realistic space physics feel, smooth motion, no subtitles, no watermark, no logo.",
            "model.ratio": "16:9",
            "model.resolution": "720p",
            "seed": 1973428150,
            "watermark": False
        },
        "_meta": {
            "title": "ByteDance Seedance 2.5 Text to Video"
        }
    },
    "2": {
        "class_type": "SaveVideo",
        "inputs": {
            "filename_prefix": "video/Seedance2.0_mini",
            "format": "auto",
            "format.codec": "auto",
            "video": [
                "1",
                0
            ]
        },
        "_meta": {
            "title": "Save Video"
        }
    }
})

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)

API documentation

Seedance 2.0 Mini: Text to Video

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

How do I keep a character consistent across multiple shots?

Where do I control the camera movement?

What video formats can I save?

Are there limits on duration, resolution, or FPS?