Back to list
videoavailableunit-only

Vidu

ShengShu

Video generation with character and reference control.

Data basis
Input → Output
text, imagevideo
Pricing unit
credits / generation
Access
consumer-appapi
Last verified
2026-09-15

Model performance benchmarks

Scores retain their original benchmark, version and metric. We do not combine them into a site-wide score; results from different versions are not directly comparable.

87.3%
Text-to-videoleaderboard-2026-09-15 · QUALITY_SCOREAs of 2025-04-21
87.9%
Text-to-videoleaderboard-2026-09-15 · SEMANTIC_SCOREAs of 2025-04-21
87.4%
Text-to-videoleaderboard-2026-09-15 · TOTAL_SCOREAs of 2025-04-21
66%
Text-to-video holisticleaderboard-2026-09-15 · COMMONSENSE_SCOREAs of 2025-04-21
56.5%
Text-to-video holisticleaderboard-2026-09-15 · CREATIVITY_SCOREAs of 2025-04-21
62.7%
Text-to-video holisticleaderboard-2026-09-15 · TOTAL_SCOREAs of 2025-04-21
Capabilities
video generationimage-to-videocharacter consistency
Pricing and plans status

Credits / subscription

Note: multimodal pricing can be seconds, generations, credits, minutes, plan allowances or enterprise contracts. It is not forced into token pricing; only verified source-backed rows appear below.

Pricing sources and usage units
credit: See official source / credit
ShengShu · Vidu official pricing
Price source
Related plans
Vidu official pricing
ShengShu · official
See official pricing source
credit
manual reference
Verified: 2026-09-15
Official pricing source