Nodaro DocsVideo models
Grok Imagine (I2V)
Grok Imagine (I2V) is a xAI video model in Nodaro for image to video, from 50 credits per run.
Grok image-to-video — stylized motion. Up to 15s.
Credits
| Tier | Credits |
|---|---|
| 6s default | 150 |
| Grok Imagine (I2V) | 50 |
| Grok Imagine (I2V) | 80 |
| Grok Imagine (I2V) | 100 |
Use Grok Imagine (I2V) in Nodaro
Add one of these nodes to your canvas, open its settings, and choose Grok Imagine (I2V) as the model:
Prompt tips
- Keep prompts simple and direct — Subject + Action + Setting + Camera + Mood. Grok expands the prompt itself; over-specification fights the expander.
- Image-to-video: the input image IS the first frame (composition, identity, and style are preserved) — describe the MOTION, don't re-describe the still.
- Video 1.5: 1-15s (default 8), 480p/720p/1080p, up to 7 input images (1080p allows only one). Native audio incl. music, SFX, and lip-synced dialogue — quote the line to have it spoken.
- Aspect ratio applies to text runs (1:1/16:9/9:16/3:2/2:3/auto); a single input image locks the output to the image's own aspect.
Similar models
| Model | Maker | Modes | Credits | Details |
|---|---|---|---|---|
| Grok Imagine Video 1.5 | xAI | Image to video | from 295 | Grok Imagine 1.5 image-to-video — 1–15s, 480p/720p, per-second pricing. Requires an input image. |
Frequently asked questions
Last updated on