logo
RunComfy
  • ComfyUI
  • Trainer
  • Models
  • MCPNew
  • Pricing
  • Seedance 2.5Hot
  • Seedream 5.5New

Workflows by Model

HotMiniMax H3Video with audio from text, images or referencesHotQwen Image 2.1Create images and edit photos with referencesWanVideo from text or images, motion transferFLUXImage generation, editing and character variationsLTXVideo with synced audio from text or imagesQwen Image EditPhoto editing with text and image referencesKrea 2Image creation, style transfer and reference editsZ-ImageFast portraits and concepts from text

Popular & New Workflows

NewMiniMax H3 Character Swap V1.5Swap video characters, keep the original audioNewP-H3-Image Reference EditEdit a photo guided by a reference imageHotMiniMax H3 Image-to-VideoOne image to cinematic video with synced audioHotLTX 2.5 Image-to-VideoOne frame to sharp video with synced audioHotMiniMax H3 Character Swap (SAM3)Swap video characters while following the motionQwen Image 2.1 Multi-Image EditingPrecise scenes from up to 10 reference imagesFLUX Klein Face SwapNatural, lifelike face swapsSeedVR2 Video UpscalerSharp, smooth video upscaling
View More Workflows

Train a Model

NewMOSS-Image BaseImage generation, newly supportedNewFLUX.3 KleinImage generation, newly supportedHotKrea 2The most-trained image modelHotKrea 2 TurboFew-step image generationHotQwen Image 2.1Image generation and editingZ-Image TurboFast portraits and concept imagesMiniMax H3Video with synchronized audio

Train & Deploy

Getting StartedYour first training job with Ostris AI ToolkitDatasetsUpload and manage training datasetsInferenceRun your trained models in a playground or via APIDeploymentsServe your trained models as dedicated endpoints
Train More Models

Image Models

NewGPT Image 2.65% OFF · Detailed text to image, GIF and SVG, up to 4KNewSeedream 5.510% OFF · Text to image up to 2K, with transparent PNGsHotSeedream 5.0 Pro41% OFF · Reference edits with multilingual textHotSeedream 4.520% OFF · Photoreal edits with brand consistencyHotWan 2.6 ImageInstruction-based image editingFLUX.2Precise, photorealistic image editsNano Banana Pro77% OFF · Precise 2K to 4K visuals from sketchesQwen Image EditLoRA-based, structure-aware image editing

Video Models

NewSeedance 2.5 Flash34% OFF · Text, image, or reference to videoNewKling 4.010% OFF · Animate a still into a 3 to 30s clipHotWan 3.0 Prime13% OFF · Fast clips from reference videosHotSeedance 2.536% OFF · Longer, more consistent cinematic videoHotWan 3.0Clips from image, video and audio referencesHotMiniMax H3Animate a first frame into a 5 to 15s clipWan 2.510% OFF · Fluid motion with native audioFLUX 3 MaxClips from text, a still, or keyframes
View More Models

API

Serverless (ComfyUI)Deploy ComfyUI workflows as serverless endpoints.Serverless (LoRA)Deploy LoRAs as serverless endpoints.Model APIRun hosted models on-demand with no deployment.Trainer APITrain, manage, and retrieve LoRAs via API.CLIRun RunComfy models from your terminal.
MODELS
Explore
All Models
LIBRARY
Generations
MODEL APIS
API Docs
API Keys
ACCOUNT
Usage

Seedance 2.0 Pro: Cinematic Text-to-Video with 2K Lip-Sync on playground and API | RunComfy

bytedance/seedance-2.0/pro

Generate cinematic 2K videos from text and media inputs with native audio, precise lip-sync, and smooth storytelling control for ads, film previz, and branded visual content.

Text prompt for the video (Chinese ~≤500 characters, English ~≤1000 words recommended).
Reference images for multimodal reference mode (0–9). Support jpeg、png、webp、bmp、tiff、gif.
Reference videos for multimodal reference mode (0–3). Support mp4、mov. Video duration must be between 2 and 15 seconds.
Reference audio for multimodal reference mode (0–3). Support wav、mp3. Audio duration must be between 2 and 15 seconds. Size should be less than 15MB.
Seedance 2.0 Pro default is adaptive (model picks closest ratio; actual ratio is returned on task query).
Integer seconds in [4, 15].
When true, the model outputs video with synchronized audio (speech, SFX, music).
Random seed for the video generation.
Idle
Billed on total video seconds (input + output). The rate per second is $0.08 for 480p, $0.175 for 720p, $0.40 for 1080p, and $0.90 for 4k. Text-to-video counts only the generated duration; when a reference video is provided, both the input and output durations are counted.

Introduction To Seedance 2.0 Pro Video Creation

ByteDance's Seedance 2.0 Pro turns text and references into cinematic videos, delivering up to 2K resolution with native audio and millisecond lip-sync. Trading manual frame-by-frame editing, masking, and separate dubbing for multimodal inputs (up to 9 images, 3 videos, 3 audio) with camera path control, multi-shot storytelling, and precise lip-sync, Seedance 2.0 Pro streamlines production by eliminating complex rotoscoping and audio alignment for marketing teams, agencies, film previz, and game studios. For developers, Seedance 2.0 Pro on RunComfy can be used both in the browser and via an HTTP API, so you don’t need to host or scale the model yourself.

Ideal for: High-Conversion Video Ads | Shot-Accurate Film Previsualization | Brand-Consistent Multi-language Lip-Synced Narratives

ByteDance Seed / Seedance 2.0 Pro#


Seedance 2.0 Pro is a multimodal text-to-video model from ByteDance Seed that turns scene descriptions and optional references into short cinematic clips. On RunComfy you drive generation with a prompt plus optional images (up to 9), videos (up to 3), and audio (up to 3) for multimodal reference mode, and you can set aspect ratio, duration, resolution, generate audio, and seed.


Output (this playground): selectable 480p / 720p / 1080p / 4K · 4–15 seconds · aspect ratios including adaptive (default), 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 · optional native audio when Generate audio is enabled


Highlights#

  • Multimodal references: Up to 9 images, 3 reference videos (2–15 s each, mp4/mov), and 3 audio references (2–15 s, wav/mp3, under 15 MB each), together with a strong text prompt.
  • Flexible framing: Default adaptive ratio lets the model pick the closest format; fixed ratios are available for platform-specific delivery.
  • Audio-aware video: Toggle Generate audio for synchronized speech, SFX, and music with the clip.
  • Controllable length: Duration is an integer from 4 to 15 seconds (default 5).
  • Reproducibility: Set Seed when you need repeatable results while refining prompts or references.

Parameters of Seedance 2.0 Pro#

Inputs match the RunComfy OpenAPI Input schema for this template.


ParameterRequiredTypeDefaultRange / OptionsDescription
prompt*Yes (*)string—CN ~≤500 chars, EN ~≤1000 words rec.Text prompt for the video
image_url (Images)Noarray (image URIs)[]0–9jpeg, png, webp, bmp, tiff, gif
video_url (Videos)Noarray (video URIs)[]0–3mp4, mov; duration 2–15 s per clip
audio_url (Audio URLs)Noarray (audio URIs)[]0–3wav, mp3; 2–15 s, < 15 MB
aspect_ratioNostringadaptiveadaptive, 16:9, 9:16, 4:3, 3:4, 1:1, 21:9Adaptive: model picks closest ratio; check task result for actual ratio
durationNointeger54–15 (seconds)Clip length in whole seconds
resolutionNostring720p480p, 720p, 1080p, 4kOutput resolution preset
generate_audioNobooleantruetrue / falseWhen true, outputs video with synchronized audio (speech, SFX, music)
seedNointeger——Random seed for video generation

How to Use Seedance 2.0 Pro#

1) Describe your scene — Cover subject, action, setting, mood, lighting, and camera. For prompt length, Chinese ~≤500 characters or English ~≤1000 words is recommended.

2) Add references (optional) — Upload images for look or identity; add short reference videos or audio. Respect duration and file-size limits for each modality.

3) Choose aspect ratio — Use adaptive for general exploration, or a fixed ratio (e.g. 9:16 or 16:9) for a known deliverable.

4) Set duration — Any integer from 4 to 15 seconds.

5) Pick resolution — 480p for fast drafts, 720p as the default balance, 1080p for high detail, or 4K for the sharpest output.

6) Generate audio — Leave enabled for dialogue, SFX, or music; disable if you only need silent video.

7) Optional seed — Fix the seed while iterating so changes come from prompt or media, not randomness.

8) Generate and iterate — Refine wording, swap references, or adjust ratio, duration, and resolution.


Prompt & Reference Tips for Seedance 2.0 Pro#

  • Be specific about camera and motion (e.g. medium close-up, slow push-in, handheld vs locked-off).
  • Use images for what must stay stable (face, costume, logo); use text for what should evolve (action, mood).
  • Reference videos and audio must be 2–15 seconds; keep reference audio under 15 MB.
  • With generate_audio on, mention dialogue tone or ambient sound you want to hear.
  • If results feel noisy or contradictory, simplify the prompt or reduce conflicting style cues.

How Seedance 2.0 Pro compares to other models#

  • Seedance 1.5 Pro: Seedance 2.0 Pro extends multimodal reference options, duration control, and cinematic motion for short clips; compare outputs on the same prompt and references.
  • Wan 2.5 / Kling Video 2.6: Pick based on whether you need this template’s mix of image, video, and audio references, lip-sync-friendly audio generation, and the parameter set above.

More Models to Try#

  • Seedance 1.5 Pro — Solid prior-generation lip-sync and short-form results.
  • Seedance 1.0 — Simple text-to-video baselines.
  • Wan 2.5 — Strong general-purpose text-to-video alternative.
  • Kling Video 2.6 — Motion editing and reference-driven action strengths.

In short, Seedance 2.0 Pro on RunComfy supports text plus up to nine images, three videos, and three audio references, 4–15 s clips, 480p–4K presets, flexible aspect ratios including adaptive, and optional native audio aligned with the live playground fields.

Related Playgrounds

ltx-2/retake-video

LTX 2 retake video modifie the video by the prompt.

wan-2-2/animate/video-to-video

Transforms input clips into synced animated characters with precise motion replication.

veo-3-1/reference-to-video

Create rapid high-quality video drafts with precise style and speed

veo-3-1/first-last-frame-to-video

Create structured cinematic clips with audio, scene links, and prompt accuracy

seedance-1.0/image-to-video

Create fluid, expressive animations with multi-shot storytelling features.

veo-3-1/extend-video

Seamlessly lengthen shots with frame-consistent context control and audio blending for refined video creation.

Frequently Asked Questions

What resolution and aspect ratio options does Seedance 2.0 Pro text-to-video expose on RunComfy?

On this playground, resolution is one of 480p, 720p (default), 1080p, or 4K. Aspect ratio can be adaptive (default—the model picks the closest ratio; the task result reflects the actual output) or fixed: 16:9, 9:16, 4:3, 3:4, 1:1, or 21:9.

What are the limits for prompts and reference media (images, video, audio)?

Prompt: Chinese ~≤500 characters or English ~≤1000 words is recommended. Images: up to 9 files (jpeg, png, webp, bmp, tiff, gif). Reference videos: up to 3 (mp4, mov), each 2–15 seconds. Reference audio: up to 3 (wav, mp3), each 2–15 seconds and under 15 MB. Only prompt is required; all reference fields are optional.

How do I move from testing in the RunComfy Playground to production API integration with Seedance 2.0 Pro text-to-video?

Use the RunComfy API with the same Input fields as the playground (prompt, image_url, video_url, audio_url, aspect_ratio, duration, resolution, generate_audio, seed). Validate prompts and media limits in the UI, then use your account API key and credits for automated jobs.

What has Seedance 2.0 Pro text-to-video improved compared to Seedance 1.5 Pro?

Seedance 2.0 Pro targets cinematic short clips with multimodal references (many images plus optional video and audio), 4–15 second duration control, flexible aspect ratios including adaptive, and native audio when generate_audio is on—useful for lip-sync and synced SFX or music. Exact benchmarks depend on your content; compare outputs on identical prompts and references.

How does Seedance 2.0 Pro text-to-video compare to models like Wan 2.5 or Kling Video 2.6?

Choice depends on your workflow. On RunComfy, this Seedance 2.0 Pro template offers up to nine images, three reference videos, three audio references, 480p–4K presets, and toggled generated audio. Wan 2.5 and Kling 2.6 differ in pricing, limits, and strengths—run parallel tests on your typical prompts and reference sets.

Can Seedance 2.0 Pro text-to-video keep characters or style consistent across a clip?

Yes, in practice reference images (and optional reference video or audio) plus a clear prompt help anchor identity, wardrobe, and tone. There is no special “@” syntax documented in the API schema; consistency comes from aligned text and reference media within the supported limits.

Does Seedance 2.0 Pro text-to-video support native audio generation and lip-sync?

When Generate audio (generate_audio) is true (the default), the model is described as outputting video with synchronized audio (speech, SFX, music). Set it to false if you only want silent video. Lip-sync quality still depends on prompt clarity and the scene you describe.

How long can each generated video be, and how is duration set?

Duration is an integer from 4 to 15 seconds (default 5). Pick any whole-second value in that range per generation.

Can I use Seedance 2.0 Pro text-to-video output commercially?

Commercial use depends on ByteDance’s licensing terms for the model and RunComfy’s terms of service. Review the official model license and RunComfy documentation, or contact hi@runcomfy.com before using generated footage in paid campaigns or public distribution.

Who benefits most from Seedance 2.0 Pro text-to-video on RunComfy?

Teams and creators who need short cinematic clips with optional image, video, and audio references, platform-specific aspect ratios, up to 4K exports on this playground, and optional built-in audio—for example ads, social video, previsualization, and branded narrative tests.

Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Video Models
  • Seedance 2.5 Flash Text To Video
  • Seedance 2.5 Flash
  • Seedance 2.5 Flash Reference to Video
  • Wan 3.0
  • MiniMax H3 Fast
  • Wan 2.5
  • View All Models →
Image Models
  • Seedream 5.5
  • Seedream 5.5 Edit
  • Seedream 5.5 Layer Decomposition
  • Wan 2.6 Image to Image
  • Nano Banana Pro
  • Seedream 5.0 Pro
  • View All Models →
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Seedance 2.0 Pro Video Examples Showcase

Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...