18 video models · 6 image models · one studio
There isn’t one model for every video: the right one depends on what yours needs. DreamBench has 18 video models and 6 image models in one studio. Filter them by sound, clip length, resolution and credits, play the clips they have made here, and put two or three side by side before you create.
Which model fits
Start from what the video needs. Each list names the models that fit it on DreamBench, and why.
These models’ pages are about speech: characters who say their lines, with lips in time.
And 2 more.
These make up to 30 seconds in one generation, long enough for a moment to play out without a cut.
Labels, signs and lettering that read: these models’ pages say they handle words in the picture.
And 1 more.
These render up to 4K on DreamBench, on the Plus, Ultra and Studio plans.
These take the fewest credits for a 10-second 720p video with sound in Film Studio. Seedance 2.5 also renders 480p, to try an idea first.
Every model can start from your pictures: DreamBench draws each clip’s opening frame from them. These take them directly, on the clip itself.
Give these a first and a last frame, and the clip moves from one to the other.
And 9 more. Show them in the finder
On the Video page your prompt goes straight to the model, one clip at a time, with no scene plan. These models are on it; every model is in Film Studio.
And 5 more. Show them in the finder
Model finder
Pick what your video needs and the list narrows as you go. Every price is what the composer quotes for a 10-second video with sound in Film Studio.
18 of 18 video models
ByteDance Seed
Tell a short story in one clip of up to 30 seconds, cut into linked shots, with sound made with the picture.
753 credits for 10 s at 720p with sound
Beauty commercial for a fictional lipstick brand "Lumière Pop," 15 seconds, 9:16 vertical, multi-shot edit with quick, rhythmic cuts. Every shot uses seamless, solid, saturated color backgrounds, soft even beauty lighting, luminous dewy skin and glossy lips. Three lipstick shades: coral orange, fuchsia pink, soft peach. Shot 1 (0–1.5s): Extreme macro close-up of a glossy hot pink lipstick tube against a magenta background. The bullet twists up slowly, revealing the angled fuchsia tip, light gliding across its creamy surface. Shot 2 (1.5–3s): Quick cut to a young woman with a sleek low bun and gold drop earrings, wearing a fuchsia satin shirt, against a magenta background. Close-up as she glides the fuchsia lipstick across her lower lip in one smooth stroke. Shot 3 (3–4.5s): Extreme close-up of her lips pressing together, then parting into a soft smile, the color rich and glossy. Shot 4 (4.5–6s): Hard color cut to orange. A young man with tousled dark hair, wearing a crisp orange shirt, against a bright orange background, turns his head toward the camera and smirks, lips tinted with a sheer coral shade. Shot 5 (6–7.5s): Top-down shot of three lipstick bullets in coral, fuchsia and peach drawing thick, creamy swatch strokes across a white surface, each stroke landing in rhythm. Shot 6 (7.5–9s): Hard color cut to sky blue. A young woman with short curly hair and small pearl earrings, wearing a pale peach knit top, against a sky blue background, applies the soft peach lipstick while looking into a small handheld mirror, then glances at the camera. Shot 7 (9–10.5s): Slow-motion shot of the three lipsticks tumbling through the air against a split background of orange, magenta and sky blue, caps spinning off, catching the light. Shot 8 (10.5–13s): All three models stand together in a tight group against a solid magenta background, shoulder to shoulder, each turning toward the camera at a slightly different moment, smiling, with a gentle camera push-in. Shot 9 (13–15s): End card. The three lipsticks stand upright side by side, each on its own vertical color block of orange, magenta and sky blue, caps beside them. Clean minimal "Lumière Pop" logo appears below in simple white text. Style: modern K-beauty campaign aesthetic, bold color blocking, crisp sharp focus, flawless but natural skin texture, glossy plump lip finish. Fresh, playful, confident and high-end. Each character and product stays consistent across shots. @lumière_pop_lipstick
Up to 30-second clips at 720p or 1080p, with sound in every clip.
No example yetKling AI
Shoot one take of up to 30 seconds, with stereo sound and dialogue in 9 languages.
603 credits for 10 s at 720p with sound
Up to 15-second clips at 720p or 1080p, with sound in every clip.
No example yetTry HeyGen's tuned version of MiniMax H3, with sound in every clip of up to 15 seconds.
333 credits for 10 s at 720p with sound
Up to 20-second clips at 720p or 1080p, with sound you can switch off.
No example yetSet the first and last frame of a clip of up to 20 seconds, with sound you can turn off.
643 credits for 10 s at 720p with sound
Up to 10-second clips at 720p, 1080p or 4K, with sound in every clip.
No example yetMake widescreen or portrait videos, with sound on every clip.
523 credits for 10 s at 720p with sound
Up to 30-second clips at 720p or 1080p, with sound in every clip.
No example yetAlibaba Cloud
Build scenes with dialogue, ambience and sound effects, in single clips of up to 30 seconds.
483 credits for 10 s at 720p with sound
Up to 15-second clips at 720p or 1080p, with sound in every clip.
No example yetTry a tuned version of MiniMax H3, with sound built in.
463 credits for 10 s at 720p with sound
Up to 15-second clips at 720p or 1080p, with sound in every clip.
No example yetMiniMax
Make scenes you want to hear as well as see, with stereo sound on every clip of up to 15 seconds.
463 credits for 10 s at 720p with sound
Up to 15-second clips at 720p or 1080p, with sound in every clip.
No example yetAlibaba
Have people speak to camera with lip-synced dialogue, in clips of up to 15 seconds.
583 credits for 10 s at 720p with sound
Up to 15-second clips at 720p or 1080p, with sound in every clip.
No example yetxAI
Animate high-energy scenes in clips of up to 15 seconds, with sound in every one.
583 credits for 10 s at 720p with sound
Alibaba Cloud
Give scenes a stylized look, from manga and pixel art to 3D animation, in clips of up to 15 seconds.
503 credits for 10 s at 720p with sound
Pixel-art animation, 16-bit style. A tiny knight sprite descends a torch-lit dungeon staircase, pixels flickering with the flames. She dodges a swinging pixel axe, hops a gap over pixel lava, and lifts the lost crown as it sparkles in a four-frame twinkle. Chiptune-adjacent bleeps as SFX only.
Up to 10-second clips at 720p, 1080p or 4K, with sound you can switch off.
No example yetLightricks
Explore abstract and ambient visuals, from watercolor to ink in water, in widescreen or vertical.
433 credits for 10 s at 720p with sound
ByteDance Seed
Follow characters through dialogue and action in clips of up to 15 seconds, guided by reference images.
523 credits for 10 s at 720p with sound
A golden retriever running through a sunlit meadow, tracking shot following alongside, golden hour lighting, cinematic and warm, shallow depth of field with wildflowers in foreground.
Kling AI
Make movement the focus, from sport and dance to vehicles, with lip-synced dialogue in 5 languages.
553 credits for 10 s at 720p with sound
A runner in electric-yellow running shoes sprints through an empty city at first light. Tight on the shoes striking wet pavement, splashing through a shallow puddle, springing off a curb. She rounds a corner into full sun and stops, breathing hard, grinning. Final shot: the shoes, mud-flecked, planted on the curb edge.
Google DeepMind
Shape realistic widescreen or vertical scenes with dialogue and sound, on Veo 3.1, Fast or Lite.
573 credits for 10 s at 720p with sound
Underwater at sunrise: light shafts sweep across a coral reef as a sea turtle glides through a school of silver fish that parts around it like a curtain. A ray lifts from the sand in a slow wingbeat of silt. The turtle rises toward the glittering surface and breaks it into the sun. Muffled underwater ambience, then one clear breath.
Google DeepMind
Google built Fast for ads, social media content and quick tests of a creative idea. Choose it for product clips, vertical posts and drafts at 720p or 1080p.
633 credits for 10 s at 720p with sound
Security camera footage from a fixed porch camera at night — grainy black-and-white infrared, a wide fisheye view of a front door, two steps and a delivered parcel, a timestamp in the top corner reading exactly "02:14:37". Nothing moves. Then a raccoon waddles into frame from the left, sniffs the parcel, looks straight up at the camera with glowing eyes, and drags the box off the step one determined tug at a time. The camera never moves; the picture stays low-resolution, noisy and slightly stuttering. No music — the hum of the night and the scrape of cardboard on concrete.
Up to 8-second clips at 720p or 1080p, with sound in every clip.
No example yetGoogle DeepMind
Google built Lite for trying ideas quickly and for making video in volume. Choose it to see how a prompt plays, or to make many short clips, before you refine it.
423 credits for 10 s at 720p with sound
Up to 10-second clips at 720p or 1080p, with background music if you want it.
No example yetShengShu Technology
Bring a cast of characters into one scene from their reference images, in clips of up to 10 seconds.
393 credits for 10 s at 720p with sound
16 credits an image, with up to 8 reference images.
No example yetOpenAI
Make everyday images, and the character, prop and location sheets your videos are built from.
16 credits per image
61 credits an image, with up to 8 reference images.
No example yetOpenAI
Put words inside the picture, from a poster headline to a speech bubble, or draw sheets for your videos.
61 credits per image
15 credits an image, with up to 8 reference images.
No example yetByteDance Seed
Make infographics, posters and photographic images, with text in many languages.
15 credits per image
4 credits an image, with up to 8 reference images.
No example yetFreeform images, and the character, prop and location sheets your videos are built from.
4 credits per image
6 credits an image, with up to 8 reference images.
No example yetGoogle DeepMind
Make posters, cards and diagrams with lettering, or design the characters and places for your next video.
6 credits per image
10 credits an image, with up to 5 reference images.
No example yetFreeform images, and the character, prop and location sheets your videos are built from.
10 credits per image
Side by side
Check Compare on two or three models in the finder to see them side by side. Until then, here is every model.
| Model | Longest clip | Resolution | Sound | First and last frame | Aspect ratios | Credits, 10 s at 720p |
|---|---|---|---|---|---|---|
| Seedance 2.5ByteDance Seed | 30 s | 480p · 720p · 1080p | On or off | Yes | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 753 |
| Kling 4.0Kling AI | 30 s | 720p · 1080p | Always on | Yes | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 603 |
| HeyGen Video 1 | 15 s | 720p · 1080p | Always on | First frame only | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 333 |
| FLUX 3 Max | 20 s | 720p · 1080p | On or off | Yes | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 643 |
| Gemini Omni Flash | 10 s | 720p · 1080p · 4K | Always on | First frame only | 16:9 · 9:16 | 523 |
| Wan 3.0Alibaba Cloud | 30 s | 720p · 1080p | Always on | Yes | 1:1 · 16:9 · 9:16 · 4:3 | 483 |
| MiniMax H3 Max | 15 s | 720p · 1080p | Always on | Yes | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 463 |
| Seedance 2.0ByteDance Seed | 15 s | 720p · 1080p · 4K | On or off | Yes | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 523 |
| Veo 3.1Google DeepMind | 8 s | 720p · 1080p · 4K | Always on | Yes | 16:9 · 9:16 | 573 |
| Veo 3.1 FastGoogle DeepMind | 8 s | 720p · 1080p | Always on | Yes | 16:9 · 9:16 | 633 |
| Veo 3.1 LiteGoogle DeepMind | 8 s | 720p · 1080p | Always on | Yes | 16:9 · 9:16 | 423 |
| HappyHorse 1.1Alibaba | 15 s | 720p · 1080p | Always on | First frame only | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 583 |
| Kling 3.0Kling AI | 15 s | 720p · 1080p | On or off | Yes | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 553 |
| Wan 2.7Alibaba Cloud | 15 s | 720p · 1080p | On or off | Yes | 1:1 · 16:9 · 9:16 · 4:3 | 503 |
| LTX-2.3Lightricks | 10 s | 720p · 1080p · 4K | On or off | Yes | 16:9 · 9:16 | 433 |
| Vidu Q2ShengShu Technology | 10 s | 720p · 1080p | Background music, on or off | First frame only | 1:1 · 16:9 · 9:16 · 4:3 | 393 |
| MiniMax H3MiniMax | 15 s | 720p · 1080p | Always on | Yes | 1:1 · 16:9 · 9:16 · 4:3 · 21:9 | 463 |
| Grok Imagine 1.5xAI | 15 s | 720p · 1080p | Always on | First frame only | 1:1 · 16:9 · 9:16 · 4:3 | 583 |
Check Compare on two or three models in the finder to see them side by side. Until then, here is every model.
| Model | Credits per image | Credits per sheet | Reference images | Plans |
|---|---|---|---|---|
| GPT Image 2.5OpenAI | 16 | 22 | Up to 8 | Every plan |
| GPT Image 2OpenAI | 61 | 83 | Up to 8 | Every plan |
| Seedream 5.0ByteDance Seed | 15 | 20 | Up to 8 | Every plan |
| Seedream 5.0 Flash | 4 | 5 | Up to 8 | Every plan |
| Nano Banana 2Google DeepMind | 6 | 8 | Up to 8 | Every plan |
| Grok Imagine Image 2.0 | 10 | 14 | Up to 5 | Every plan |
Still have questions?
18 video models: Seedance 2.5, Kling 4.0, HeyGen Video 1, FLUX 3 Max, Gemini Omni Flash, Wan 3.0, MiniMax H3 Max, Seedance 2.0, Veo 3.1, Veo 3.1 Fast, Veo 3.1 Lite, HappyHorse 1.1, Kling 3.0, Wan 2.7, LTX-2.3, Vidu Q2, MiniMax H3 and Grok Imagine 1.5. And 6 image models: GPT Image 2.5, GPT Image 2, Seedream 5.0, Seedream 5.0 Flash, Nano Banana 2 and Grok Imagine Image 2.0. The finder on this page filters them by sound, clip length, resolution and credits, and 16 of them have a page of their own with prompts to start from.
The one that fits the video. For one long take, Seedance 2.5, Kling 4.0 and Wan 3.0 make up to 30 seconds at a time. For a 4K finish, Gemini Omni Flash, Seedance 2.0, Veo 3.1 or LTX-2.3. To put your own pictures on every clip, Seedance 2.5, Seedance 2.0, Veo 3.1 or Vidu Q2. The finder filters by what your video needs.
Every video model on DreamBench can generate sound. On Kling 4.0, HeyGen Video 1, Gemini Omni Flash, Wan 3.0, MiniMax H3 Max, Veo 3.1, Veo 3.1 Fast, Veo 3.1 Lite, HappyHorse 1.1, MiniMax H3 and Grok Imagine 1.5 it is always on. On Seedance 2.5, FLUX 3 Max, Seedance 2.0, Kling 3.0, Wan 2.7 and LTX-2.3 you switch it on or off per video. Vidu Q2 adds background music only.
Their developers list the languages their speech holds up in: Seedance 2.5 (11 languages), Kling 4.0 (9 languages) and MiniMax H3 (11 languages). The other models with sound can speak a line you write too; DreamBench lists no languages for them.
Gemini Omni Flash, Seedance 2.0, Veo 3.1 and LTX-2.3 render up to 4K on DreamBench, on the Plus, Ultra and Studio plans. Every other model renders at 720p or 1080p, and every plan from Starter up renders at least 720p.
Seedance 2.5, Kling 4.0, HeyGen Video 1, FLUX 3 Max, Gemini Omni Flash, Wan 3.0, MiniMax H3 Max, Seedance 2.0, Veo 3.1 Fast, Veo 3.1 Lite, HappyHorse 1.1, Kling 3.0, Wan 2.7, LTX-2.3, Vidu Q2, MiniMax H3 and Grok Imagine 1.5, and every image model, are on every plan from Starter at $9.99 a month. Veo 3.1 needs Plus, Ultra or Studio.
Seedance 2.5, Kling 4.0 and Wan 3.0 up to 30 seconds; FLUX 3 Max up to 20 seconds; HeyGen Video 1, MiniMax H3 Max, Seedance 2.0, HappyHorse 1.1, Kling 3.0, Wan 2.7, MiniMax H3 and Grok Imagine 1.5 up to 15 seconds; Gemini Omni Flash, LTX-2.3 and Vidu Q2 up to 10 seconds; Veo 3.1, Veo 3.1 Fast and Veo 3.1 Lite up to 8 seconds. A whole DreamBench video can be longer, because the scenes are generated one by one and joined: up to 30 seconds on Starter, 2 minutes on Plus and 5 minutes on Ultra and Studio.
Each is what the composer quotes for a 10-second video with sound in Film Studio: 183 credits for planning the video and drawing its references, plus the model’s rate per second. A Video page clip is the model’s seconds alone, priced on its own. You always see the exact cost before you generate.
Pick one model for each video and DreamBench uses it for every scene, so the look holds from the first shot to the last. To try another model, make a new video from the same idea, or build its characters with an image model first and reuse the sheets.
Make your video
Every model on this page is in the same studio. Describe the video you have in mind, then change the scenes you want to improve.
