Video Model — text, image & multimodal-to-video
Seedance 2.5 is ByteDance's next-generation video model, succeeding Seedance 2.0 as its top contender alongside Veo and Kling. Its headline is native 30-second generation in a single pass (from 4–30 seconds).
Reference control is the other jump: up to 50 multimodal inputs per request, up from 12 — images, video, and audio, each assigned a job in the prompt. The same reference stack drives generation, editing, and extension. Audio is co-generated in the same generation as the visuals, so dialogue, music, and effects land in sync. Prompt adherence is roughly 20% better than 2.0.
Unlimited Access & Plan Terms
Which plans include Seedance 2.5 Unlimited
- AI Creator Annual (80,000 credits/month) and above
- AI Professional Monthly (500,000 credits/month) and above
- Max Pro / Max Pro Teams plans at the 80,000-credit tier or higher
What "Full Year" actually means
"Seedance 2.5 Unlimited — Full Year" means: for up to 12 months from your purchase or activation date, generations with this model don't draw from your credit balance — as long as your subscription stays active. It is not a stored or transferable benefit. If you cancel or your subscription lapses, Unlimited access to Seedance 2.5 ends immediately, even if part of the 12 months remains.
What Unlimited does not cover
Reference-to-Video (uploading image, video, or audio references to guide generation) always uses credits, on every plan, regardless of whether you have Unlimited access to Seedance 2.5. Text-to-Video and Image-to-Video are the only modes covered by Unlimited.
Parallel (simultaneous) generations
Each plan tier has a concurrency limit that applies whether you're generating with Unlimited or with credits. Upgrading to a higher tier raises this limit.
[Flag for Product: ticket history shows conflicting numbers here — 5 vs. 8 simultaneous generations for the same plan tier, depending on which article or agent the customer reached. This needs one authoritative number before it goes back out publicly.]
Fair use and daily limits
Unlimited generations are subject to reasonable-use limits that vary by model and reset daily at midnight UTC. We don't publish a fixed daily number today. If you reach the threshold, Unlimited pauses until the next reset — you can continue generating using credits in the meantime. Your monthly Fast Generation allowance (see plan details) is separate from Unlimited and refreshes every month.
[Optional addition, pending confirmation from Data/Product: if usage data shows most customers never come close to the daily threshold under normal creative use, saying so here would directly address the most common pre-purchase objection — "what's the actual number?" Don't add this line unless it's backed by real data.]
If Unlimited access to this model changes during your subscription term
Model availability under Unlimited can change over time. We don't currently guarantee a pro-rated refund or account credit if Seedance 2.5's Unlimited status changes or is removed during a paid term — your subscription's standard refund policy applies. We'd rather say this plainly here than have customers find the ambiguity themselves in the Terms of Service.
API / MCP integrations
Unlimited access currently applies only to generations made directly through the Artlist AI Toolkit or Artlist Studio. Generations made through the Artlist MCP integration (e.g., via Claude) always use credits, even on a plan with Seedance 2.5 Unlimited. There's currently no setting to change this.
Future model versions
If a future version (for example, a potential Seedance 3.0) is released during your subscription term, whether it's included under your existing Unlimited access depends on how that model is added to the plan lineup at the time. The current offer covers Seedance 2.5 specifically and doesn't guarantee coverage of future versions.
Variants at a Glance
| Type | Modalities | Max Res. | Talking Points | |
|---|---|---|---|---|
| 2.5 (new) | Video gen / edit / extend | T2V, I2V, first & last frame, multimodal refs (image / video / audio) | 720p | Native 30s single pass, no stitching; up to 50 reference inputs (30 img / 10 vid / 10 aud); timestamped video editing; forward, backward & bridge extension; native audio co-generation; ~20% better prompt adherence |
| 2.0 | Video gen / edit / extend | T2V, I2V (+ audio / video refs) | 4K | Caps at 12 reference inputs; shorter native duration ceiling; live on Artlist today |
Seedance 2.5 is the model documented here; all Key Features and Technical Capabilities below describe 2.5. Seedance 2.0 is shown for comparison only.
Key Features
Generation Modes
- Text-to-Video (T2V): Generate video from a text prompt
- Image-to-Video (I2V): Text prompt plus a first-frame image
- Reference-to-Video (R2V): Upload up to 50 reference inputs (up to 30 images, 10 video clips, and 10 audio clips) to guide generation — use them to define subjects, background, style, camera movement, or soundtrack. See "Unlimited Access & Plan Terms" above — R2V always uses credits.
- First & Last Frame: Text prompt plus first-frame and last-frame images; if the two aspect ratios differ, the first frame wins and the last frame is auto-cropped
- Native 30s in one pass: A full 30-second clip is generated in a single pass — no stitching, no scene-cut splicing, no seams
- Multi-shot generation: Generate several shots with cuts between them from a single prompt
- Multimodal reference generation: Feed image, video, and audio references and specify in the prompt what each is for — subject, background, composition, style, camera movement, motion, dialogue, music, or SFX.
Editing & Extension
- Video editing: Replace subjects, add / remove / modify elements, or locally redraw regions — driven by reference materials plus the prompt
- Timestamped edits: Scope a change to a time window — "replace 0:02–0:05" — leaving the rest of the clip untouched
- Forward extension: Continue a clip on from its last frame, holding style, rhythm, and camera logic
- Backward extension: Generate the moment before a clip, using its first frame as the endpoint
- Seamless bridge: Take two clips and generate the missing transition between them
- Task-type intelligence: The model infers the task (generate / edit / extend) from the prompt. Duration semantics differ: generate and edit = total output; extend = the extended portion only
Smart Controls
- Adaptive aspect ratio: Industry-exclusive — T2V picks the best ratio from the prompt; first-frame tasks match the input image; multimodal reference picks from the first recognized media file (video over image)
- Smart Duration: The model can pick an appropriate length in the 2–30s range
- Prompt adherence: Roughly 20% better than 2.0 — fewer generations before a usable result
Technical Capabilities
| Duration | Any integer 4–30s per clip, generated natively in a single pass. Smart Duration (-1) auto-picks 4–15s. |
|---|---|
| Resolution & color | 720p at 24 FPS. 10-bit color depth. |
| Aspect ratios | 16:9, 9:16, 4:3, 3:4, 1:1, 21:9, or Adaptive (model chooses). If a specified ratio differs from an uploaded image's, the image is center-cropped. |
| Reference inputs | Up to 50 total = 30 images + 10 videos + 10 audio clips. Images: 0–30, up to 4K each. Videos: 0–10, up to 4K each, 2–30s per clip, total under 30s. Audio: 0–10, 2–30s per clip, total under 30s. Video and audio totals are counted separately. |
| Audio | Native — co-generated in the same latent space as visuals; audio references can drive dialogue, music, and SFX. |
| Spoken languages | English, Chinese, Spanish, Indonesian, Malay, Thai, Arabic, Portuguese, Vietnamese, Japanese, Korean. |
Limitations
- Single clip is capped at 30s — long-form still needs to be assembled from multiple generations
- 720p / 24 FPS and 10-bit color are not yet confirmed for our integration
- Reference video and reference audio are each capped at 30s total per request (each file 2–30s)
- If a specified aspect ratio differs from an uploaded image's, the image is center-cropped; in first & last frame mode a mismatched last frame is auto-cropped
- The ~20% prompt adherence gain is a vendor-stated figure, not something we've benchmarked
- Pre-release — treat every number here as provisional
Prompting Tips
- State clearly in the prompt which reference materials to use and for what — subject vs style vs motion vs audio — the model follows your assignments
- With 50 reference slots available, be deliberate rather than exhaustive: a few well-labelled references beat a pile of unlabelled ones
- Use Adaptive aspect ratio for text-to-video when the target placement is unknown — the model picks the best ratio from the prompt
- Set an explicit duration when output length matters; Smart Duration (-1) decides for you
- For first & last frame generation, match the aspect ratios of both images — otherwise the last frame is auto-cropped to fit the first
- For edits, give a timestamp range to scope the change and add "keep everything else unchanged" so the model doesn't touch unrelated areas
- Describe the audio you want in the prompt — dialogue, music, and SFX are co-generated with the visuals, not added in a separate pass