Skip to content
← Models
ClosedByteDance/10 trustVerified
Jimeng logo

Jimeng

ByteDance's AI creative platform for image and video generation, home of Seedance.

Visit official page →

About

Jimeng (internationally known as Dreamina) is ByteDance's AI-powered creative platform for generating and editing images and videos from text, image, and video inputs. Launched on desktop in May 2024 with a mobile app following in August, it became the consumer home for ByteDance's Seedance video model line, including the global Seedance 2.5 launch in July 2026 with 30-second continuous generation and up to 50 multimodal reference assets.

The honest picture: Jimeng is a platform entry in the models catalog because ByteDance does not sell the underlying models separately; the generation models are proprietary and API/platform-only, with no open weights. It competes directly with Kling, Vidu, and Pika in the AI video space, and early reviews noted inconsistent output quality. Pricing is subscription and credit-based, varying by market. For catalog purposes it represents ByteDance's first-party creative generation models as served through Jimeng and Dreamina.

Specs

Context window

Pricing

Free quota

API access

Weights

Closed — API only

Released

August 1, 2024

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

ai-video-generationtext-to-imagecreative-editingcontent-creation

Trust score — 8/10

/10 trustVerified

Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 117; Trending score 80/100 from researcher assessment.

Sources