Seedance 2.5
Seedance 2.5 creates a clip from a written description or from one starting image, with whole-second lengths from 4 to 30 seconds and three quality tiers.
Clip length: 4–30s · Audio: Sound can be switched on or off
Every model here has its own clip length, quality tiers, sound handling and control set. These guides describe what each one offers today, so you can choose before spending credits.
These guides cover selected models available in the workspace. More guides will be added as they are reviewed; the workspace lists all available models.
Clips generated from a description or animated from a single starting image. Length range, quality tiers and sound handling differ from model to model.
Seedance 2.5 creates a clip from a written description or from one starting image, with whole-second lengths from 4 to 30 seconds and three quality tiers.
Clip length: 4–30s · Audio: Sound can be switched on or off
MiniMax H3 turns a description or a single starting image into a clip of 4 to 15 seconds that carries a generated sound track.
Clip length: 4–15s · Audio: Sound is always generated
Wan 3.0 is the standard variant of the Wan 3.0 family on this platform: a wide length range, three quality tiers and shape control in both text and image mode.
Clip length: 2–30s · Audio: Sound can be switched on or off
Wan 3.0 Prime is the second selectable product in the Wan 3.0 family: the same controls and length range as the standard variant, quoted at a higher credit rate.
Clip length: 2–30s · Audio: Sound can be switched on or off
PixVerse V6 Max renders clips from a single second to fifteen, across four quality tiers, from a description or from one uploaded still.
Clip length: 1–15s · Audio: Sound can be switched on or off
A preview video model that renders clips from 1 to 15 seconds in three quality tiers, from a description or one starting image.
Clip length: 1–15s · Audio: No audio on/off control
Images generated from a description or edited from your own references. Quality tiers, shape options and background control differ from model to model.
One of the two selectable GPT Image 2.5 products on this platform: text and reference-based image generation with transparent-background support at the 1K tier.
Quality tiers: 1K · 2K · 4K · Reference images: 16
The second selectable GPT Image 2.5 product: the same tiers, shapes, background control and credit prices as Flare, with this guide focused on editing your own images.
Quality tiers: 1K · 2K · 4K · Reference images: 16
Nano Banana 2.1 covers both workflows on one model: images from a description, or edits driven by up to ten of your own reference images, at 1K, 2K or 4K.
Quality tiers: 1K · 2K · 4K · Reference images: 10
The FLUX 3 family product available on this platform: text generation and reference editing at 1K, 2K or 4K, with PNG, JPEG and WebP output.
Quality tiers: 1K · 2K · 4K · Reference images: 10
All models draw on the same credit balance. The workspace shows the exact cost of the settings you picked before you confirm a task, and the pricing page lists the current credit packages.
See credit packagesOpen a workspace, pick a model from the selector and read the quote before you generate. Every guide on this page links to the workspace entry it describes.