Introduction
Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity. Gen-4.5 currently offers Text to Video and Image to Video control, with support for additional inputs coming soon.
The model excels at understanding and executing complex, sequenced instructions. You can specify detailed camera choreography, intricate scene compositions, precise timing of events and subtle atmospheric changes— all within a single prompt.
This article outlines Gen-4.5 details, access, and more. To review prompt examples and their results, please see our Camera Terms, Prompts, & Examples guide.
Related links
- Introduction to Prompting
- Text to Video Prompting Guide
- Image to Video Prompting Guide
- Camera Terms, Prompts, & Examples
Gen-4.5 spec details
Text to Video |
Image to Video |
|
| Plan requirement | Standard and higher | |
| Cost | 12 credits per second | |
| Supported durations | 2 - 10 seconds | |
| Infinite generations in Explore Mode | Yes | |
| Platform availability | Web | |
| Base prompt inputs | Text | Text & Image |
| Supported aspect ratios | 16:9 — 1280x720 px | 16:9 — 1280x720 px |
| Output resolution | 720p | |
| Frame rate (FPS) | 24fps, 25fps | |
Step 1 — Accessing Gen-4.5
Gen-4.5 can be accessed through multiple creation modes. Click each dropdown to learn more about access through your preferred creation mode:
Video Tool Mode
Navigate to Video creation mode, then select Gen-4.5 from the model selector dropdown in the bottom left-hand corner.
Workflows
To use Gen-4.5 in Workflows, click the add (+) button and select a Gen-4.5 Text to Video or Gen-4.5 Image to Video node.
Step 2 — Drafting the prompt
To use Image to Video, first upload an image by dragging and dropping it to the prompt window. For Text to Video, you only need to enter a text prompt.
Enter in a prompt that describes the scene you wish to create in clear, direct language.
- Image to Video prompts should focus on describing the motion of the scene
- Text to Video prompts should describe both the visual elements and motion of the scene
For more information on prompting and best practices, please see our comprehensive collection of prompting guides:
- Introduction to Prompting
- Text to Video Prompting Guide
- Image to Video Prompting Guide
- Camera Terms, Prompts, & Examples
Step 3 — Generating and iterating
Before generating, review the settings to confirm proper configuration for your shot:
- Aspect Ratio — Accommodates your input image by default, but may be changed to crop the input.
- Duration — Select a duration between 2 and 10 seconds. Prompts that request multiple sequential actions may benefit from longer durations.
- FPS — Choose between 24 or 25fps in the Advanced settings.
Click the Generate button to begin processing the generation. Once the generation completes, favorite, upscale, or download the output using the controls beneath the right side of the output:
Continue working on the result by selecting the Use button towards the left-hand side beneath the generation:
You may iterate by making prompt adjustments to further refine the results. For more information on iteration and prompt troubleshooting, please see our Introduction to Prompting guide.