FLORA Academy
EDITOR
TEXT MODELS
IMAGE MODELS
Gemini 2.0 Flash
Topaz
Magnific
Seedream
Flux Dev
GPT-Image (OpenAI)
Nano Banana aka GPT 2.5 Flash Image (Google)
VIDEO MODELS
Runway Gen-4 (Runway)
Cinematic image & video generation focused on reference consistency and character continuity.
Quick facts
Modes: Text + Reference Image → Image · Image → Video · Video → Video · Image → Image.
Default output / size: TBD
Aspect ratios: TBD
What it’s great for
Generating consistent characters from reference images.
High-quality image-to-video and video-to-video transformations.
Production-ready compositing and VFX workflows.
Example outputs
![]() | ||
Reference character consistency
| Scene generation
| Video frame example
|
Copy-and-paste prompts
Create cinematic close-up of character from reference image, maintain facial consistency across lighting
Image-to-video: gentle camera pan around the subject, 5s, cinematic grade
Edit: replace background with rainy city street, motion-matched reflections
Parameters
Name | Type | Default | Notes |
| string | — | Required |
| string | — | For reference-based generation |
| string | TBD | 21:9, 16:9, 1:1, 4:3, 3:4, 9:16 |
| select | TBD | 5 seconds, 10 seconds |
| seed / integer | — | Optional |
Modes
Mode | Estimated time | Required inputs | Typical use |
Image → Video | 1 minute |
| Animate stills |
Video → Video | 4 minutes |
| Restyle or reanimate video |
Text → Image (if reference image is provided) | 45~60 seconds |
| Character / environment generation |
Output options
Option | Values / notes |
Aspect ratio | 21:9, 16:9, 1:1, 4:3, 3:4, 9:16 |
Formats | Image, Video |
Notes | Reference consistency and production workflows: TBD |
Prompt tips
Include “from reference image” when asking for character consistency.
Specify shot motion and duration for video endpoints.