FLORA Academy

Master FLORA. Go beyond the fundamentals to the tools, techniques, models, and workflows behind professional creative work.

EDITOR

Quickstart

TEXT MODELS

GPT-5

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

Kling 2.1

Runway Gen-4

Seedance

VEO 3

Moonvalley Marey

Runway Gen-4 (Runway)

Cinematic image & video generation focused on reference consistency and character continuity.

Modes: Text + Reference Image → Image · Image → Video · Video → Video · Image → Image.
Default output / size: TBD
Aspect ratios: TBD

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

Name	Type	Default	Notes
`prompt`	string	—	Required
`image_url`	string	—	For reference-based generation
`aspect_ratio`	string	TBD	21:9, 16:9, 1:1, 4:3, 3:4, 9:16
`duration`	select	TBD	5 seconds, 10 seconds
`seed`	seed / integer	—	Optional

Mode	Estimated time	Required inputs	Typical use
Image → Video	1 minute	`image_url`, `prompt`	Animate stills
Video → Video	4 minutes	`video_url`, `prompt`	Restyle or reanimate video
Text → Image (if reference image is provided)	45~60 seconds	`Prompt, reference image`	Character / environment generation