The Complete Google Flow Course: Beginner to Pro

Learn to create, edit, and retouch images with Flow’s NanoBanana image models—NanoBanana Lite, NanoBanana 2, and NanoBanana Pro—producing consistent characters and locations through multi-generation prompts and versatile aspect ratios.

Prompt what you want to create images with Nanobanana, using styles, shots, lighting, and direction to shape results. Organize assets, rename generations, and manage upscaling and downloads across plans.

Explore enhancing prompts for image generation by setting task context, using prompt templates, and requesting text responses; compare Gemini and Cloud agents for better results.

Edit images and generate variations with a reshooting model, manage edits via a history timeline, save copies to a workspace, and refine prompts for quality results.

Learn to use draw tools: pencil, annotations, and box selection to reinforce prompts, edit images with doodles, and extend or outpaint the scene using Nano Banana.

Use box and lasso selections to replace objects, and crop to cut the image without creating a version. Enhance with NanoBanana and manage edits for storyboard references while tracking quality.

Explore how using a reference versus locking an ingredient affects image generation, showing how references guide style while locks enforce subject consistency.

Learn to use grids to create consistent prompts across subjects, animals, and products, build a reference sheet with prompts for objects like a Gibson Les Paul guitar, and handle branding.

Create and manage consistent characters by building visual descriptions and AI-like voices, then reuse across projects with templates, prompts, and body and outfit details for seamless workflows.

Explore how to use filters and settings to organize assets, switch between grid and batch views, adjust size and sound options, and manage prompts for efficient workflow.

Explore flow video models, comparing frames, ingredients, and text-to-video, with Veo 3.1 variants and OmniFlash, noting time limits, credits, and drafting in light mode before quality.

Discover text-to-video in flow, use prompts with ingredients, compare vo 3.1 lite and opni models, and note reliability, lack of references, and upscaling options.

Master extending videos in the complete Google Flow course by learning to create new scenes with VO 3.1 or OmniFlash, manage frames and prompts, and download cohesive sequences.

Master prompting for video by using a style, composition and framing template with ambience and lighting, camera motion, and dialogue to craft realistic prompts that AI can follow.

Master frames to video to control your clip by setting starting and ending frames, keeping the background consistent, and choosing between Veo and OpniFlash for seamless transitions.

Learn how the ingredients method delivers consistency across video subjects and scenes by prompting for actions, locking ingredients, and balancing VO3 and OmniFlash limits.

Learn to combine four ingredients with references to generate a video, compare locking and non-locking settings, and craft prompts in authentic UGC style for consistent results.

Edit videos with omni flash by prompting directly, since dedicated editing tools are deprecated. Simple prompts yield reliable results, while complex edits may be inconsistent and cost 20 credits.

Manage a project agent to generate images and videos by using sessions, defaults, and instructions; brainstorm prompts and build storyboards for eight-second videos.

Learn to generate a storyboard script and a visual storyboard grid with the agent, using prompts and references, then refine assets like Mike, coffee cup, and sunglasses.

Learn batch generation with the agent to create multiple product shots and videos from one image, edit them via collections, and apply a warmer tone across 16:9 and 9:16.

Set up agent instructions to define a Wes Anderson style with color palette, lighting, art direction, and subject direction, then toggle instructions per project so generated images follow the rules.

Learn how the agent organizes assets by renaming files, trashing items, and creating collections, using conversational prompts to manage images and videos in Google Flow.

Explore Google Flow’s ai tools for images, video, and prompting, including experimental options and custom variations via the agent, via Discover and My Tools, with a paid subscription.

Sketch with pencil tools, undo, redo, and add gallery images; describe your image with additional information to generate realistic results. Use Scene Explorer to brainstorm train station style, Wes Anderson.

Explore shot explorer and mask magic tools to generate varied camera shots from a reference image, brush selections, prompts, and image edits with version history.

Explore converge and the grid architect to retexture images, convert sketches to vector layers, generate multiple vector versions, and build cinematic grid stories with a prompt wizard.

Explore ai video tools in Google Flow, applying shader fx and colorize, then create type overlays by adding and animating text layers; adjust finishing options and export the mp4.

Create animated video sketches by drawing on a layered canvas, importing media, adjusting colors and brush settings, and applying animations, then explore transitions and weirdcore effects before rendering.

Explore the video resizer, StringOut creator, and video granulator to import media, adjust canvas formats, build timelines with text layers, and apply granular glitches and audio-visual effects.

Explore AI prompting tools with character x-ray and style writer to generate wardrobe and psychological profiles from images, apply feedback and edits to craft stronger characters.

Discover how the storyboard studio auto-generates scripts, assets, and storyboards from prompts, while you edit characters, locations, and props and refine scenes through regen and autofill.

Learn how to build organized prompts with a prompt tree, detailing subject, action, setting, and style, then generate and iterate images and storyboards using a story sketch workflow.

Overlay a dynamic white 2D hand-drawn doodle animation onto a dancing subject, using prompts and style descriptions. Promote four synchronized interactions: footwork, arm sweeps, body popping, and a final jump.

Learn to generate motion variations by altering style and prompts, using the agent or Gemini, with options like 2D hand-drawn doodles, 3D wireframes, digital waves, glitch and smoke.

Turn video frames into reference doodles by capturing snapshots, editing with red doodles, and converting them into clean white hand-drawn lines for motion graphics using prompts and timestamps.

Master stop-motion collage animation by crafting in-and-out transitions with reference images and precise prompts. Use Google Flow, Opni Video Generator, and NanoBanana to generate host, co-hosts, and cat scenes.

Design a clothing commercial by selecting outfits, uploading subject images, and guiding a model through a posed walk with prompt-driven visuals, background control, and frame-based video planning.

Create the second scene of a modern clothing commercial by setting the subject in new clothing and location, using Gemini and NanoBanana prompts for pose, background, and camera movement.

Master scene three by crafting three shot variations, guiding a steady medium wide push-in, with eye contact and focus rack for a premium clothing commercial, using AI video.

Edit a clothing commercial in DaVinci Resolve by assembling scenes 1–4, cutting and speeding clips, syncing to the track, and marking key poses with music rights awareness.