Seedance 2.0 Mini
ByteDance's lightweight AI video model — cinematic 4–15s clips with native audio, camera control, and multimodal references at half the cost of Seedance 2.0.
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-mini-image-to-video-basic",
"prompt": "Aerial drone shot over a misty mountain valley at golden hour"
}'
# Use the returned queue_id with https://api.venice.ai/api/v1/video/retrieve.
# Call /video/complete after downloading if needed.Overview
What is Seedance 2.0 Mini
Seedance 2.0 Mini is ByteDance's lightweight AI video model, released June 15, 2026, as a cost-efficient tier in the Seedance 2.0 family. It generates 4–15 second cinematic clips from text, images, or references, supports native audio and camera control, and outputs at 480p or 720p — ideal for high-volume, short-form content creation.
Using it anonymously on Venice
On Venice, Seedance 2.0 Mini runs under an anonymized privacy tier — your prompts are not stored, profiled, or used for training. This enables permissionless, uncensored video generation at scale, perfect for social, marketing, or prototyping workflows where privacy and iteration speed matter. No account sign-up is required.
Specifications
Datasheet
- Maker
- ByteDance
- Modality
- Text-to-video, image-to-video, reference-to-video
- Open weights
- No — proprietary
- License
- Proprietary
- Clip lengths
- 4s – 15s
- Resolutions
- 720p, 480p
- Mode
- image-to-video
- Audio
- Yes
- Prompt limit
- 10,000 chars
- References
- Up to 9 images, 3 video clips, and 3 audio files
- Reference video
- 15 seconds total maximum
- Released
- June 15, 2026
- Privacy on Venice
- Anonymized — prompts not stored
- Available on Venice since
- Jun 2026
Assessment
Strengths and limitations
- Cost-efficient for high-volume generation: priced at roughly half of Seedance 2.0 Standard, enabling more iterations per budget.
- Fast generation: optimized for sub-minute turnaround on 10-second clips, ideal for rapid prototyping.
- Cinematic quality with AI camera control: supports zooms, pans, and dynamic framing driven by prompt.
- Strong multimodal input support: guide outputs with up to 9 images, 3 videos, and 3 audio files as references.
- Native audio generation: produces synchronized dialogue, sound effects, and music in the same pass as video.
- Limited to 720p max resolution: not suitable for 4K or cinema-grade deliverables.
- Closed and proprietary: no open weights, so self-hosting or fine-tuning is not possible.
- No support for clips longer than 15 seconds: not designed for long-form content.
Use cases
What it is good for
- 01High-volume social media content creation with consistent branding.
- 02Rapid prototyping of video concepts and storyboards.
- 03Animating still images into short cinematic clips with motion and sound.
- 04Generating marketing drafts where cost and speed outweigh 4K fidelity.
- 05Creating short-form videos with synchronized dialogue and sound effects.
Prompting
Getting better results
Use camera direction keywords like 'zoom in', 'pan left', or 'dolly forward' to control motion.
Enclose spoken dialogue in double quotes to trigger synchronized audio generation.
Upload a first and last frame to guide the start and end state of the animation.
Reference assets as [Image1], [Video1], [Audio1] in your prompt for precise control.
Set duration to -1 to let the model choose the optimal clip length.
Use 'adaptive' aspect ratio to let the model pick the best fit for your input.
Samples
Sample outputs
Generated on Venice with our standard prompt suite — the same prompts we run through every model of this type, so you can judge it like-for-like.
Slow aerial drone shot gliding over a misty mountain valley at golden hour, sunlight piercing clouds onto a winding river, ancient pine forests on either side, ultra-smooth motion, professional color grading, atmospheric haze, 4K
Calm ocean waves rolling onto a black-sand beach at sunrise, golden light on wet sand, foam dissolving into the shore, a single silhouetted figure at the waterline, smooth continuous forward push, serene cinematic atmosphere
A slow tracking shot through a rain-soaked Tokyo street at night, neon reflecting in puddles, steam rising from a food cart, a person with a translucent umbrella, shallow depth of field, teal-and-orange grade, smooth steady camera
Alternatives
How it compares
| Model | Best for | Max duration | Max resolution | Native audio |
|---|---|---|---|---|
| Seedance 2.0 Mini | High-volume, low-cost clips | 15s | 720p | Yes |
| Grok Imagine 1.5 | Cinematic quality | 15s | 1080p | Yes |
| Wan 2.7 Enhanced | Open weights, high fidelity | 15s | 1080p | Yes |
| Vidu Q3 | Longest single take | 16s | 1080p | Yes |
Choose Seedance 2.0 Mini when you need fast, low-cost video generation at scale — ideal for social drafts, prototyping, and high-volume workflows where 720p is sufficient.
API
Call it from your code
Venice exposes this model through the REST API. Queue a generation with the model id.
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-mini-image-to-video-basic",
"prompt": "Aerial drone shot over a misty mountain valley at golden hour"
}'
# Use the returned queue_id with https://api.venice.ai/api/v1/video/retrieve.
# Call /video/complete after downloading if needed.Pricing
What it costs on Venice
Pay per clip on Venice — price scales with resolution and duration (4s–15s), from $0.18.
New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.
FAQ
Frequently asked questions
Seedance 2.0 Mini is ByteDance's lightweight AI video model, released June 15, 2026. It generates 4–15 second clips from text, images, or references, supports native audio and camera control, and outputs at 480p or 720p — ideal for high-volume, short-form content creation.
On Venice, Seedance 2.0 Mini starts at $0.18 per clip for 480p · 4s, with prices scaling by resolution and duration. The model is billed per clip, making it cost-efficient for high-volume use.
No. Seedance 2.0 Mini is a proprietary model by ByteDance — not open source and not free. It cannot be self-hosted or fine-tuned. On Venice, you pay per clip with no subscription required.
Yes. The variant seedance-2-0-mini-image-to-video-basic supports animating a still image into motion, with optional control over the first and last frame of the clip.
Seedance 2.0 Mini supports 480p and 720p outputs. It does not support 1080p or 4K — for higher resolutions, use Seedance 2.0 or Seedance 2.5.
Yes. It generates native synchronized audio, including dialogue, sound effects, and background music. Put speech in double quotes in your prompt to trigger lip-synced audio.
Yes. The reference-to-video variant accepts up to 3 video clips as input, with a maximum total duration of 15 seconds. These can be referenced in the prompt as [Video1], [Video2], etc.
Yes. The model variant seedance-2-0-mini-image-to-video-basic is specifically designed for image-to-video animation, allowing you to turn a still image into a 4–15 second cinematic clip.
Seedance 2.0 Mini is cheaper and faster, with native audio, but capped at 720p. Wan 2.7 is open weights and supports 1080p, but lacks native audio. Choose Seedance for speed and sound, Wan for openness and resolution.
Use Seedance 2.0 Mini anonymously
Venice does not store your prompts. Chat history stays in your browser.