Skip to main content
Kyeo AI
AI video model
ByteDance
Seedance

Seedance 2.0 Mini

Seedance 2.0 Mini combines text, first/last-frame, and multimodal-reference generation in one entry point. Reference video enters the pre-task pricing formula, so both media duration and output duration must be verified before task creation.

Use this modelView credit pricingBack to Model Hub
Scene
Text / first-last frames / references
Output
480p / 720p
Duration
4–15 seconds
Credits
15–150
30-second overview
  • Three mutually exclusive scenes prevent fields from being mixed
  • Accepts up to 9 images, 3 videos, and 3 audio clips
  • Reference-video duration is included in preauthorization
  • Web search is available only in text mode

Popular searches: How do I use Seedance 2.0 Mini? · How much does Seedance 2.0 Mini cost? · How many videos can Seedance 2.0 Mini accept?

Examples

Cinematic scene

Use a high-saturation anime pop aesthetic. Combine Japanese animation title design, Y2K sticker graphics, colorful graffiti lettering, cute character-like typography and energetic motion design. Typography style: The main text “Kiki” should be the visual focus. Create a unique hand-drawn bubble graffiti lettering style with soft inflated shapes, rounded organic silhouettes and playful exaggerated proportions. The letters should feel alive, like a mascot or anime character. Use thick white sticker outlines, dark outer borders, glossy highlights, candy-like textures, tiny sparkles, halftone dots, comic patterns, hand-drawn imperfections and colorful graphic decorations. The secondary name “Mayz” appears underneath as a smaller handwritten signature, feeling like an artist’s personal mark. Color palette: high-saturation anime colors: hot pink, cherry red, electric blue, lime green, sunny yellow, warm cream and small black accents. Avoid corporate logo design. Avoid minimalist typography. Avoid luxury branding. The lettering should feel youthful, creative, energetic and connected to anime illustration culture. Timeline: 0–1.2s — Start with a vibrant abstract anime graphic background. Colorful paint splashes, sticker fragments, comic shapes and small doodle elements rapidly appear. The screen feels like an animated sketchbook coming to life. 1.2–3.0s — A burst of colorful particles gathers toward the center. The handwritten bubble letters of “Kiki” begin forming piece by piece, bouncing into place with playful squash-and-stretch animation. Each letter has its own expressive movement. 3.0–4.5s — The complete “Kiki” wordmark appears large in the center. The letters wobble slightly like soft 3D stickers. Small stars, sparkles, hearts, comic lines and colorful graphic elements orbit around the typography. 4.5–6.5s — The camera pushes rapidly into the letters. Extreme close-ups reveal candy textures, hand-drawn patterns, glossy highlights and tiny animated details inside the typography. The screen transitions through colorful graphic wipes. 6.5–8.5s — The composition resets. “Mayz” appears underneath “Kiki” as a stylish handwritten creator signature. The two names lock together with energetic motion, surrounded by anime-style effects, sticker shapes and dynamic lines. 8.5–10.5s — The typography breaks apart into colorful fragments, then reforms in different playful variations. Add fast cuts, rotation, elastic motion, comic impact frames and animated doodles. 10.5–13.0s — Show oversized cropped sections of “Kiki · Mayz” filling the screen. Alternate between bright color backgrounds and darker contrast frames. Add manga-inspired speed lines, halftone textures and glitch-like animation accents. Animation style: smooth 2D motion graphics, anime opening title sequence energy, hand-drawn illustration feeling, playful squash-and-stretch, dynamic typography animation, clean graphic shapes, high frame-rate movement. Editing: frame-accurate cuts, energetic transitions, typography-based wipes, graphic explosions, elastic motion, quick zooms, comic impact flashes and rhythmic movement synced to the beat. Sound: upbeat electronic anime opening style, energetic percussion, playful synths, glitch clicks, impact sounds, colorful whooshes and typography hits. No people, no characters, no 3D realistic objects, no corporate branding, no minimal logo presentation, no gradients, no unreadable text.

Cinematic scene

NESQUIK STRAWBERRY SHAKE AD FORMAT: 15s / 5 SHOTS / strawberry milk — speed, energy, pure joy SUBJECT: Anthropomorphic cartoon Pink Panther, tall upright body, sleek pink fur, expressive eyes, playful smile, iconic long tail. Wearing a bright yellow sports jersey with blue side panels and small N logo, blue trousers, grey sneakers with blue laces. Smooth premium 3D cel-shaded animation, soft lighting, exaggerated cartoon proportions. HERO PROPS: Yellow plastic bottle with pink cap, “Strawberry Lowfat Milk” label (pink band, white logotype, strawberry graphic, Pink Panther illustration, 8 fl oz). Clear glass tumbler filled with rich creamy pink strawberry milk with light froth. ENVIRONMENT: Vast sunny meadow with rolling green grass, oversized daisies, tulips, and pink flowers. Clear deep blue sky with soft clouds. A flowing strawberry-pink milk stream winds through the background over smooth rocks. Warm saturated fantasy world with slightly oversized vegetation. MOOD: Pure joy and exhilaration from discovery to first sip. MUSIC: Bouncy orchestral pop with bright brass, playful woodwinds, rhythmic lift, ending in a warm sustained chord. COLOR PALETTE: Pink, yellow, sky blue, meadow green, creamy strawberry tones. Bottle and jersey visually linked. STYLE: Premium 3D animated commercial, soft volumetric sunlight, sharp product focus in close-ups, smooth cinematic motion, consistent costume and label orientation, no extra characters. SHOT 1 (0:00–0:03, WS, 24mm) Pink Panther runs through the meadow with an energetic stride, tail flowing behind. Camera tracks alongside as oversized flowers blur past. The pink strawberry-milk stream glistens in the distance. Pink Panther briefly glances at camera with a playful grin. SHOT 2 (0:03–0:06, MS, 50mm) Pink Panther slides to a stop beside the strawberry stream. He notices a bright yellow strawberry milk bottle resting near a giant flower. Eyes widen with excitement. He picks up the bottle with both hands and raises it toward the sunlight. SHOT 3 (0:06–0:09, CU–MCU, 85mm) Bottle label faces camera perfectly. Pink Panther twists open the pink cap and pours smooth strawberry milk into the glass tumbler. Creamy pink liquid flows elegantly, froth forming at the top. Warm sunlight intensifies around the product. SHOT 4 (0:09–0:12, MCU, 50mm) Pink Panther takes a satisfying drink. Eyes close with delight. After the sip, one eye opens in a playful wink. He smiles broadly and points directly toward the camera, inviting viewers to join the fun. SHOT 5 (0:12–0:15, HERO CU PULL BACK, 85mm) Hero product shot. Strawberry milk bottle and frosty glass rest on lush grass, label facing camera. Camera slowly pulls back to reveal Pink Panther crouched behind them in a playful pose. Oversized flowers frame the composition. Golden sunlight creates a warm glow as the music resolves on a joyful final chord.

Cinematic scene

SUBJECTS: Female Olympic-level diver @ image 1. Slightly stylized cartoon proportions, clean athletic hair bun, no swim cap, competition swimsuit. ENVIRONMENT: International-level diving competition venue. Deep blue pool, 10-meter platform, audience seating, judging area, and intense stadium lighting. The water surface must feel realistic: the sensation of air brushing across the water, subtle reflections, extremely thin water entry traces, tiny ripples, and lingering bubbles should all exist naturally. MUSIC: Steady rhythmic percussion combined with low-frequency ambient music. STYLE: Digital painting aesthetic. Large simplified color blocks, hard-edge brushwork, low-detail structure, heavy shadows, preserving visible hand-painted texture. No realistic 3D feeling, no commercial CG advertisement look, no polished realism. SHOT 1 35mm, close-up of the edge of the 10-meter platform. The camera slowly approaches from a low side angle of the platform. The diver has already completed the handstand preparation pose at the platform edge, both hands firmly supporting the platform, shoulders and back fully opened, core tightened, legs together extending upward into a clean straight line. SFX: Subtle stadium ambience, quiet breathing from the audience, low-frequency ambient music begins. SHOT 2 50mm, close-up to medium shot. The camera slowly moves from the palms to the shoulders and back, then lifts upward following the motion. She presses both hands against the platform, coordinating force through the shoulders, core, and hips as her body naturally leaves the edge of the platform. Her legs remain together and fully extended throughout, with light and stable movement. SFX: Hands contacting the platform, subtle air movement, low-frequency rhythm enters. SHOT 3 35mm, medium-wide aerial shot. The camera steadily follows her trajectory after leaving the platform. She transitions naturally into continuous flips following the takeoff motion. Her body first tightens to complete the rotation, then naturally opens into extension. Her legs sweep past overhead while her pointed toes maintain steady control. SFX: Music layers gradually rise, wind sound intensifies, subtle audience gasps. SHOT 4 28mm, high-angle tracking medium shot. The camera lightly follows her descending trajectory from above. She gradually slows the rotation, brings her arms back closer to the body, then smoothly draws them upward above her head. Her shoulders and back open as the body slowly returns to a vertical position. SFX: Music gradually leaves empty space, subtle compressed air sound, stadium ambience remains. SHOT 5 70mm, close-up of the water surface, fixed high-speed camera. Both hands cut into the water first, followed by the head, shoulders, body, legs, and pointed toes entering the pool along the same line. Only an extremely thin trace and subtle ripples remain on the water surface. Almost no splash escapes outward. SFX: Short water entry sound, low underwater thump, audience applause slowly emerges. SHOT 6 24mm, underwater medium shot. The camera slowly drifts forward following tiny bubbles. She maintains a standard streamlined glide forward, arms extended ahead, hands together. Her body then slightly relaxes as the shoulders and back guide a slow turn. Tiny bubbles create soft trailing lines along the arms, shoulders, back, and legs. SFX: Low underwater ambience, soft ambient music, tiny bubble sounds. SHOT 7 50mm, front medium close-up. The camera steadily and slowly pushes closer. She regains her stance and slowly raises her head. One hand rests near the chest while the other naturally extends upward to the side, forming a frozen finishing pose. SFX: Final rhythmic beat of the music, subtle shutter freeze sound, continuing audience applause.

Cinematic scene

Main Subject: Young Korean woman in her early 20s with a natural everyday appearance. She wears a faded charcoal-grey sleeveless crop top, loose high-waisted light-wash jeans, black canvas sneakers, and a black cord necklace. Her black wavy hair is tied in a messy side ponytail with wispy bangs. Realistic skin texture, minimal makeup, warm and approachable personality. Maintain identical identity, clothing, hairstyle, and facial features throughout the entire video. Style: Ultra-realistic smartphone home video footage. Natural mobile phone camera quality with slight authentic handheld shake, casual framing imperfections, smooth natural motion, and unpolished weekend home-video aesthetics. No cinematic polish or professional effects. Location: Small Korean home courtyard during a peaceful weekend morning with soft natural sunlight, potted plants, fallen leaves, and subtle ambient breeze. 0–3s: She casually sweeps fallen leaves from the concrete courtyard while the handheld camera gently sways, capturing a candid moment. 3–6s: The camera accidentally frames only half of her body as the autofocus briefly hunts before naturally correcting itself, preserving the authentic smartphone-recording feel. 6–9s: She waters several potted plants while smiling softly as sunlight reflects naturally from the leaves and watering can. 9–12s: She wipes sweat from her forehead, laughs naturally at the person filming, and briefly brushes loose strands of hair from her face. 12–15s: She picks up the watering can and walks back inside the house as the recording abruptly ends like a genuine weekend memory. Audio Design: - Soft morning birdsong. - Gentle breeze moving through leaves and plants. - Natural footsteps on concrete. - Water pouring softly from the watering can. - Subtle clothing movement and ambient courtyard sounds. - Quiet candid laughter and realistic smartphone audio characteristics. Visual Quality: - Ultra-realistic smartphone footage. - Slight handheld camera shake. - Authentic autofocus breathing. - Natural lighting and shadows. - Realistic skin texture and physics. - Stable character consistency throughout. - Smooth natural motion with zero cinematic effects. Negative Prompt: CGI, cartoon style, unrealistic skin, excessive beauty filters, cinematic lighting, overprocessed footage, distorted anatomy, extra fingers, flickering frames, inconsistent face or clothing, unnatural motion, low resolution, frame glitches, artificial shadows, plastic skin texture, excessive camera stabilization, text, watermark, logo, oversaturated colors, professional studio effects, unrealistic environments, duplicated objects, and identity inconsistencies.

Cinematic scene

Create an ultra-photorealistic luxury cinematic travel film featuring the same young beautiful Korean woman throughout. Preserve identical face, natural skin pores, realistic hair physics, soft almond eyes, subtle expressions, and perfect outfit continuity. She wears a cream wool trench coat, beige knit sweater, ivory tailored trousers, white leather sneakers, a minimalist silver watch, and carries a taupe leather weekender bag. Location: A real panoramic luxury train traveling through the Swiss Alps during blue hour into sunrise. Snow-covered pine forests, frozen lakes, old stone bridges, alpine villages, light winter fog, and warm golden sunlight. Sequence: 0–2s: Helicopter-style aerial beside the moving train crossing snowy mountains. 2–4s: Camera naturally glides through the panoramic window into the cabin. She quietly watches the mountains as sunrise reflections move across the glass. 4–6s: DSLR macro of her fingertips touching the cold window. Condensation disappears beneath her fingers. Beautiful creamy bokeh. 6–9s: Stabilized handheld orbit as the train crosses a dramatic stone bridge above a turquoise river. Stunning natural parallax through the windows. 9–12s: The train stops at a hidden alpine station. She steps onto the snowy platform while the train slowly departs behind her. 12–15s: Long-lens shot of her walking beside a frozen lake toward a wooden cabin. Camera slowly cranes into a breathtaking aerial reveal of the Swiss Alps. Camera: Sony FX3, Sony G Master lenses (24mm, 50mm, 85mm, 90mm Macro, 135mm). True full-frame DSLR look, natural handheld micro-shake, organic focus pulls, realistic motion blur, authentic exposure breathing, shallow depth of field. Lighting: Natural sunrise, volumetric fog, HDR, realistic reflections. Music: Emotional cinematic ambient score with soft felt piano, warm synth pads, subtle strings, gentle pulses, wordless female vocal textures, gradually building to the final aerial reveal. Ambient: Train wheels, wind, birds, footsteps on snow. Style: Netflix luxury travel documentary, 4K HDR, 24fps. Negative: No CGI, no plastic skin, no AI artifacts, no oversaturation, no impossible camera moves, no text, no logos, no watermark.

Cinematic scene

Scene Breakdown — Cinematic Color Grading Series One Western woman, nine moods — a study in color grading, cinematography, and visual storytelling Character Consistency: A beautiful Western woman in her late 20s with long wavy blonde hair, natural features, expressive eyes, elegant yet effortless style. She remains the exact same person across all nine scenes, maintaining identical facial structure, hairstyle, and identity while changing only the mood, lighting, wardrobe details, and cinematic environment. Scene 1 — "Golden Path" Tone: Warm, nostalgic, tender Lighting: Natural golden hour light diffused through thin clouds, soft directional sunlight, cinematic naturalism Camera & Lens: 35mm format, 50mm f/1.4 prime lens, shallow depth of field Scene: The blonde woman walks along a quiet countryside path, gentle breeze moving through her wavy hair, wearing a soft linen dress and a peaceful expression. Warm nostalgic color grading with golden highlights and soft shadows. Scene 2 — "Neon Crossing" Tone: Sleek, mysterious, cinematic-noir Lighting: Urban neon street lighting, wet pavement reflections, dramatic rim lighting, cinematic noir lighting Camera & Lens: Anamorphic cinema lens, 35mm equivalent, shallow depth of field, anamorphic flares Scene: The same blonde woman stands at a rainy city intersection at night, wearing a stylish dark coat, neon colors reflecting across her face, mysterious confident expression, cinematic noir atmosphere. Scene 3 — "Glass Plaza" Tone: Calm, minimalist, composed Lighting: Overcast daylight, subtle negative fill, soft gradual light fall-off Camera & Lens: Medium format aesthetic (Phase One-style), 85mm f/2.8 lens, sharp focus Scene: The woman stands inside a modern glass plaza wearing a minimalist neutral outfit. Her wavy blonde hair frames her face, calm posture, clean architectural background, refined editorial photography style. Scene 4 — "Bright Street" Tone: Energetic, vibrant, confident Lighting: Mixed ambient and natural commercial lighting, bright and inviting, perfect exposure Camera & Lens: High-end digital mirrorless, 70-200mm zoom, compressed perspective, corner-to-corner sharpness Scene: The blonde woman walks through a lively city street, wearing fashionable casual western-inspired clothing, smiling confidently, vibrant colors, luxury lifestyle campaign aesthetic. Scene 5 — "Night Market" Tone: Chaotic, spontaneous, raw Lighting: Direct on-camera hard flash, pitch-black background, harsh specular highlights Camera & Lens: Point-and-shoot digital aesthetic, 24mm wide-angle lens, slight distortion Scene: The woman explores a crowded night market, candid expression, holding street food, messy movement, flash photography style, realistic imperfections, raw documentary feeling. Scene 6 — "Greenhouse Bloom" Tone: Dreamy, delicate, joyful Lighting: Bright overcast natural lighting, backlit ethereal glow, no harsh shadows Camera & Lens: 50mm f/1.2 prime lens, extremely shallow depth of field, soft optical focus Scene: The blonde woman stands among flowers inside a greenhouse, wearing a flowing pastel dress, sunlight glowing through plants, dreamy romantic atmosphere, soft focus beauty. Scene 7 — "Rooftop Dusk" Tone: Dramatic, contemplative, powerful Lighting: Directional dusk light, dramatic chiaroscuro, atmospheric haze Camera & Lens: 35mm f/1.4 prime lens, sharp subject isolation, deep background depth of field Scene: The woman stands on a rooftop overlooking the city at sunset, wearing a structured jacket, wind moving through her blonde waves, powerful cinematic portrait with emotional depth. Scene 8 — "Pastel Spin" Tone: Carefree, nostalgic, playful Lighting: Direct harsh sunlight backlighting, heavy lens flare, hazy atmosphere Camera & Lens: 35mm consumer film camera aesthetic, soft focus lens, light leaks Scene: The blonde woman spins through a colorful outdoor setting, wearing a vintage-inspired outfit, laughing naturally, nostalgic summer film photography style. Scene 9 — "Quiet Café" Tone: Introspective, peaceful, warm Lighting: Overcast soft diffused lighting, gentle window light Camera & Lens: Medium format film aesthetic, soft vintage lens, shallow depth of field Scene: The same woman sits alone in a cozy café near a window, wavy blonde hair softly illuminated, holding coffee, thoughtful expression, warm vintage cinematic mood. Final Instruction: Create one continuous character across nine distinct cinematic color grading styles. Maintain the exact same Western woman with wavy blonde hair, facial identity, and natural beauty throughout all scenes. Ultra-realistic photography, cinematic composition, high detail, professional color grading, 8K realism.

At a glance

Is this model right for you?

First/last-frame input and reference media are mutually exclusive. Reference videos and audio clips must each be 2–15 seconds, with separate aggregate limits of 15 seconds. Images and videos are also checked for dimensions, aspect ratio, pixel count, and FPS, and noncompliant input is rejected before credits are reserved.

What it does best
A video generation option with a lower-resolution tier and controlled multimodal media limits.
Who it is for
A good fit for multi-asset storyboards, short clips with audio references, and cost-sensitive concept testing.
Why use it on Kyeo AI
The upload path verifies true formats and media metadata, while trusted durations produce a preauthorization that does not underestimate the request.

Key facts

Quickly evaluate whether this model fits your business use case.

Reference images
Up to 9
Reference videos
Up to 3; ≤15 seconds total
Reference audio
Up to 3; ≤15 seconds total
Web search
Text mode only

Other names

The same model may have different names in official documentation, community discussions, and API integrations. This section brings them together for you.

Seedance 2 Mini
Seedance 2.0 Mini
Seedance 2.0 Mini multimodal

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

How do I use Seedance 2.0 Mini?
How much does Seedance 2.0 Mini cost?
How many videos can Seedance 2.0 Mini accept?
What image formats does Seedance 2.0 Mini support?
How does web search work in Seedance 2.0 Mini?

Decision guide

Still deciding? Start with these key decision points.

1
Choose Mini for short, multi-asset work

Mini provides a compact multimodal workflow when both reference-video and reference-audio totals stay within 15 seconds.

2
Compare 2.5 when limits are too low

If you need more media or a 30-second boundary, compare Seedance 2.5.

3
Verify media geometry first

Reference videos must satisfy not only format and duration rules, but also pixel-count, dimension, and FPS contracts.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

How do the duration and media limits of Seedance 2.0 Mini and Seedance 2.5 differ?
How does Seedance 2.0 Mini pricing compare with MiniMax H3?

Model comparison table

Not sure which model to choose? Compare the key differences between this model and its alternatives at a glance.

Reference-media limits
Seedance 2.0 Mini
9 images / 3 videos / 3 audio clips
Seedance 2.5
30 images / 10 videos / 10 audio clips
MiniMax H3
9 images / 3 videos / 3 audio clips

Real-world experience

Practical guidance based on public sources, current on-site limits, and representative tasks.

Video input changes the rate

A reference video adds billable duration and switches the request to the corresponding video-input per-second rate.

More modalities require stricter upfront validation

Signed metadata binds upload results to the user, model, and media URL, reducing the risk of client-supplied duration being forged.

Capabilities

First/last-frame generation

Use a first frame or both first and last frames to guide the clip's visual start and finish.

Multimodal references

Combine images, video, and audio as reference signals.

Verifiable pricing

Verified reference-video duration is included in preauthorization through a signed token.

Use cases

Multi-asset concept clip

Use a character image, motion video, and mood audio to test a direction quickly.

First-to-last-frame transition

Plan a short transition between two key frames.

Vertical content draft

Choose 9:16 and limit the number of events for a mobile-first clip.

Prompt tips

Assign each asset a role

State whether each media type supplies the character, motion, camera, or sound reference.

Keep one timeline

Describe actions in sequence within 4–15 seconds instead of stacking conflicting events.

Use search only with text

Do not submit first/last frames or reference media when web search is required.

Why choose it

Supports a complete range of multimodal reference types.
Input counts and geometry boundaries are explicit.
Separate video-input and no-video pricing formulas are transparent.
Media authenticity is validated before task creation.

What to know first

Reference-video and reference-audio totals are each capped at 15 seconds.
Maximum output resolution is 720p.
Web search cannot be used with first/last-frame or reference scenes.
Automated checks do not replace human copyright and safety review.

Adjustable settings

Quickly evaluate whether this model fits your business use case.

Generation scene
Optional
Parameter type: Select
Default: text
Text
First frame / first and last frames
Multimodal references
Resolution
Optional
Parameter type: Select
Default: 720p
480p
720p
Video duration
Optional
Parameter type: Integer
Default: 5 seconds
4–15 seconds

Credit cost

15–150 credits

Without a reference video, billing uses output seconds. With reference video, it uses verified total reference-video duration plus output duration. The 480p rate is 3.8 credits per second without video and 2.4 with video; the 720p rate is 8.2 without video and 5 with video. Kyeo rounds the total up and settles against actual consumption after completion.

Credit-saving tip

Before generating images or videos in bulk, run an A/B test with the same input on this model and similar alternatives. Confirm the result first to avoid wasting credits.

Frequently asked questions

Related models

Still deciding? Take a quick look at these similar alternatives.

Seedance 2.5

Seedance 2.5 combines a 30-second boundary, higher media counts, and video-editing reference input in one strict scene contract. Automatic duration is not underestimated at the 5-second default; Kyeo preauthorizes against the 30-second maximum.

AI video model
102–5,700 credits
View detailsUse now

MiniMax H3

MiniMax H3 offers 768P and 2K output with text, first/last-frame, and image/video/audio reference scenes. Reference-video duration and every input image from image 6 onward affect pre-task authorization.

AI video model
32–406 credits
View detailsUse now

Kling 3.0 Turbo

Kling 3.0 Turbo targets 3–15-second video generation. It uses text mode when no image is uploaded and switches to image-to-video when one valid image is supplied. Resolution and duration directly determine the preauthorization amount.

AI video model
54–338 credits
View detailsUse now

Sources

This page is based on vendor materials, model-family documentation, and Kyeo AI integration settings.

Source note

Explore Seedance 2.0 Mini: 480p or 720p, 4–15 seconds, first/last frames, up to 9 images, 3 videos, and 3 audio clips, 15–150 credits, and upload limits. Without a reference video, billing uses output seconds. With reference video, it uses verified total reference-video duration plus output duration. The 480p rate is 3.8 credits per second without video and 2.4 with video; the 720p rate is 8.2 without video and 5 with video. Kyeo rounds the total up and settles against actual consumption after completion.

Last updated: 2026-08-28
Seedance 2 Mini current interface notes
Integration

Used to check the input modes, visible controls, media limits, and availability of the version currently connected to this site. The page and workbench show the actual options.