Can I try Seedance 2.0 Mini for free on SeeGen AI?
Yes. New users can receive 200 free credits after signing up and joining the SeeGen AI Discord. That is enough for approximately a 10-second Seedance 2.0 Mini video at 720p with no video input.
Cheapest tier · 480p/720p native
Seedance 2.0 Mini (sd2-mini) is the lowest-cost Seedance 2.0 tier on SeeGen AI, with multimodal references and native 480p/720p generation.
It is designed for cost-sensitive workflows, high-volume generation, testing, and content production where native high-resolution output is not required.
Available workflows:
Seedance 2.0 Mini supports image, video, and audio references for multimodal video generation.
| Modality | Limit | Formats | Constraints |
|---|---|---|---|
| Images | Up to 9 | JPEG, PNG, WebP, GIF, BMP, TIFF, HEIC | Max 30 MB each; shortest side ≥ 400 px |
| Videos | Up to 3 | MP4, MOV | Max 50 MB each; each video 2–15s; total duration ≤ 15s |
| Audio | Up to 3 | MP3, WAV | Max 15 MB each; each file 2–15s; total duration ≤ 15s |
Note: Total reference assets across all modalities must not exceed 12. Audio cannot be used as the only reference; at least one image or video is required.
| Parameter | Type | Default | Options / Description |
|---|---|---|---|
| prompt | string | — | Text description of the video. Max 20,000 characters. |
| urls | string[] | — | Reference image asset:// URIs. Supports up to 9 images. |
| videoUrls | string[] | — | Reference video asset:// URIs. Supports up to 3 videos. |
| audioUrls | string[] | — | Reference audio asset:// URIs. Supports up to 3 audio files. Audio cannot be used alone. |
| videoInputMode | string | "keyframe" | "keyframe" for image / first-last frame generation; "reference" for multimodal reference generation. |
| mode | string | — | Omit for standard generation; use "edit" for video editing or "extend" for video continuation. |
| duration | string | "5s" | Output duration from "4s" to "15s". |
| resolution | string | "auto" | auto, 720x720, 720x960, 960x720, 1280x720, 720x1280, 1280x540. |
| outputResolution | string | "720p" | 480p, 720p, 1080p, 2k, 4k. Mini is native at 480p/720p; higher tiers are automatically upscaled by SeeGen AI. |
| generateAudio | boolean | true | Generate synchronized speech, sound effects, and background music. Set false for silent video. |
| bitrateMode | string | "standard" | "standard" or "high". High bitrate increases file size but does not affect pricing. |
| seed | integer | -1 | -1 or omit for a random seed; 0–2147483647 for a fixed seed. |
Limited-time offer
Lowest-cost Seedance 2.0 generation. See the pricing table for current rates.
The rates below are calculated based on the $500 API Pack (125,000 credits, $0.004/credit).
| Condition | Rate | 10-sec clip |
|---|---|---|
| SD2-Mini 480p, no video input | 4.5 credits/sec (~$0.018/sec) | ~45 credits (~$0.18) |
| SD2-Mini 480p, with video input | 3.5 credits/sec (~$0.014/sec) | Based on output + reference video duration |
| SD2-Mini 720p, no video input | 9 credits/sec (~$0.036/sec) | ~90 credits (~$0.36) |
| SD2-Mini 720p, with video input | 7 credits/sec (~$0.028/sec) | Based on output + reference video duration |
| SD2-Mini 1080p (upscaled), no video input | 29 credits/sec (~$0.116/sec) | ~290 credits (~$1.16) |
| SD2-Mini 2K (upscaled), no video input | 39 credits/sec (~$0.156/sec) | ~390 credits (~$1.56) |
| SD2-Mini 4K (upscaled), no video input | 49 credits/sec (~$0.196/sec) | ~490 credits (~$1.96) |
For 1080p, 2K, and 4K output, SeeGen AI automatically upscales the native 720p generation. Upscaling adds 20 / 30 / 40 credits per output second, respectively.
1. No video input
credits = out × rate2. With video input
credits = (out + in) × rateout = output_seconds. in = the sum of ⌈duration⌉ for each input video. Each duration is rounded up, with a minimum input duration of ceil(out × 2 / 3). For upscaled output, add the upscale cost based on output duration.
3. Upscaled output (added on output duration)
1080p: + out × 20
2K: + out × 30
4K: + out × 40Generate a video in two steps: create a generation task, then query the result using the returned taskId.
If your generation uses reference images, videos, or audio files, upload them as assets first and wait until their status becomes ACTIVE. Then use the returned asset:// URIs in your request.
urlsvideoUrlsaudioUrlsAll reference assets must be reviewed and ACTIVE before use.
curl -X POST https://seegen.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SEEGEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sd2-mini",
"inputs": {
"prompt": "A cinematic tracking shot through a rainy Tokyo street at night, neon reflections on wet pavement, pedestrians walking under umbrellas.",
"duration": "5s",
"resolution": "auto",
"outputResolution": "720p",
"bitrateMode": "standard",
"generateAudio": true,
"seed": -1
}
}'Use the returned taskId to check the task status. When the status becomes COMPLETED, the generated video is available in output[0].url.
curl \
-H "Authorization: Bearer $SEEGEN_API_KEY" \
"https://seegen.ai/api/v1/jobs/queryTask?taskId=YOUR_TASK_ID"A completed task returns status: "COMPLETED" and the generated video URL in output[0].url.
Seedance 2.0 Mini is designed for cost-sensitive and high-volume workflows where minimizing credit usage is the priority.
| Use Case | Why Mini Fits | Multimodal References | Video Editing | Native Audio |
|---|---|---|---|---|
| Batch Video Generation | Generate large volumes of videos at the lowest Seedance 2.0 credit cost | Reuse products, characters, and styles across batches | Update reusable templates and variants | Generate synchronized audio automatically |
| Prompt Testing | Test more prompts, shots, and concepts before using higher-cost models | Compare different reference combinations | Quickly refine generated concepts | Test dialogue, music, and SFX |
| Content Automation | Reduce cost for recurring or automated video workflows | Maintain consistent assets across repeated tasks | Refresh templated content efficiently | Add audio without a separate workflow |
| Ad Variations & A/B Testing | Produce multiple creative variants with lower cost | Keep products and brand identity consistent | Swap products, text, backgrounds, or scene details | Generate multiple audio variations |
| Draft & Previsualization | Create inexpensive drafts before final production | Preview characters, environments, and compositions | Test edits and scene changes early | Preview the complete audio-video concept |
Seedance 2.0 Mini is best for batch generation, testing, automation, and drafts where the lowest possible credit usage matters more than generation speed.
Seedance 2.0 Mini focuses on the lowest credit cost, while Seedance 2.0 Fast prioritizes faster generation and rapid iteration.
| Feature | Seedance 2.0 Mini | Seedance 2.0 Fast |
|---|---|---|
| Model ID | sd2-mini | sd2-fast |
| Best for | Lowest-cost, high-volume generation | Faster generation and frequent iteration |
| Maximum duration | Up to 15 seconds | Up to 15 seconds |
| Reference inputs | Up to 9 images + 3 videos + 3 audio | Up to 9 images + 3 videos + 3 audio |
| Native resolution | 480p, 720p | 480p, 720p |
| Higher resolutions | 1080p, 2K, 4K upscaled | 1080p, 2K, 4K upscaled |
| 480p, no video input | 4.5 credits/sec (~$0.018/sec) | 11 credits/sec (~$0.044/sec) |
| 720p, no video input | 9 credits/sec (~$0.036/sec) | 22 credits/sec (~$0.088/sec) |
| 480p, with video input | 3.5 × (out + in) | 8.5 × (out + in) |
| 720p, with video input | 7 × (out + in) | 17 × (out + in) |
Choose Mini for lower credit usage and batch generation; choose Fast for faster turnaround.
Yes. New users can receive 200 free credits after signing up and joining the SeeGen AI Discord. That is enough for approximately a 10-second Seedance 2.0 Mini video at 720p with no video input.
Lowest-cost Seedance 2.0 generation. See the pricing table for current rates.
The per-modality limits are not additive. You can use up to 9 images, 3 videos, and 3 audio files, but the combined total cannot exceed 12 reference assets.
No. Seedance 2.0 Mini requires at least one image or video when audio references are used.
Yes. Mini generates natively at 480p and 720p. SeeGen AI can automatically upscale the result to 1080p, 2K, or 4K.
Yes. Reference images, videos, and audio files must first be uploaded as assets and become ACTIVE before use. Real human references are supported after asset approval.
Choose Mini when minimizing credit usage is the priority, especially for batch generation, testing, and automation. Choose Fast when faster generation and turnaround are more important.

Next-generation multimodal reference · native 1080p · up to 4K

Faster video generation · up to 30 seconds · 480p / 720p

High-fidelity video · up to 4k

Faster & cheaper · 480p/720p native

Fast all-in-one video · native 480p/720p/1080p · up to 30s

All-in-one multimodal video · native 480p/720p/1080p · up to 30s

4–15 seconds · up to 2K · multimodal references

5–15 seconds · 480p / 768p · native audio

5–15 seconds · 480p / 768p · native audio

1–15 seconds · up to 1080p · audio

1–15 seconds · text or one image · audio

3–30 seconds · 720p / 1080p · 10 keyframes · image and video references

1K / 2K · 10 reference images

1K / 2K · 10 reference images

Fast generation and editing · 1K/1.5K/2K · free reference images

Realistic skin and lighting · clearer small text · consistent editing

Up to 4K · 14 reference images

Fast image generation and editing

Detailed image generation and precise edits

Quality tiers · up to 4K

Fast generation · up to 4K

Highest quality · up to 4K

Fast generation · 2K/4K

High fidelity · 1K/2K