BaiduVideo modelAvailable
ERNIE-Wizshot-ME
Summary
ERNIE-Wizshot-ME generates video from a reference image, text, and audio. Baidu lists durations of four to 15 seconds and output up to 1080p. The model focuses on facial close-ups and subtle micro-expressions.
Qianfan charges CNY 0.7 per generated video second. Its API runs asynchronously: create a job, then query its result. The reviewed product page gives no exact release date or separate API model ID.
Similar models
More models of the same kind as ERNIE-Wizshot-ME, chosen by model line, developer, size, price and release date.
- MiniMax H3MiniMax · popular in this category
- LTX-2.5Lightricks · popular in this category
- Grok Imagine VideoxAI · popular in this category
- Veo 3.1 FastGoogle · popular in this category
- Muse VideoMeta · popular in this category
- Grok Imagine Video 1.5xAI · popular in this category
- FLUX.3 VideoBlack Forest Labs · popular in this category
- Sora 2OpenAI · popular in this category · no longer current
All specifications
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Shutdown
- None announced
- no source
API
- API model ID
- A separate API model ID is not listed on the reviewed product and pricing pages.
- Source: API model ID
Further details
- Focus
- For facial close-ups and natural micro-expressions such as eyebrow, mouth, and gaze movements.
- Source: Focus
- API workflow
- Two-step asynchronous workflow: create a job, then query its result.
- Source: API workflow
Prices
- Price per video second
- CNY 0.7 per generated video second.Source