In the trenches, hands-on as it happens.
Take a photo. Write a prompt. Get a marketing clip.
That is the output. Two ingredient images and one prompt. Google Flow is genuinely free to start and it works.
What is Google Flow?
Google Flow sits under the Google Labs umbrella — separate from Google AI Studio, which targets developers with a free GPT-like playground.
Create a project to get started:
The interface is familiar but the project options are less so:
The two-ingredient model
Flow combines two inputs — ingredients:
- A source image — PNG, JPG, WebP, HEIC, or AVIF
- A text prompt — your instructions for the Veo model
You can use both together (image-to-video) or either alone (text-to-video, image-only). The examples below use both.
Example 1: Professional business clip
Starting from scratch with no real photo — using ChatGPT image generation as the first ingredient.
Step 1: Generate the source image
That prompt goes into ChatGPT image generation:
Step 2: Check your constraints first
Before writing the video prompt, look at the generation settings — aspect ratios, duration, and credit cost.
Expanders and aspect-ratio presets are available:
Video length is not explicitly documented — plan for 6–8 second clips.
Step 3: Write and optimize the video prompt
Goal: a 6–8 second clip of the businessman saying “Stay informed about regulatory changes, stay compliant.”
A confident mid-40s businessman in a modern high-rise office with large floor-to-ceiling windows and a soft city skyline in the background. He is wearing a tailored navy suit and white dress shirt, standing at a slight angle with one hand in his pocket. Natural daylight, cinematic soft lighting, shallow depth of field, professional corporate style.
The camera is a slow, subtle push-in from chest-up framing. He looks directly into the camera with a calm, reassuring expression and speaks clearly and confidently:
“Stay informed about regulatory changes, stay compliant.”
His lips sync naturally to the speech. Minimal hand movement, slight nod at the end. Neutral office ambience, no background distractions. High realism, corporate brand video aesthetic, sharp focus on face, soft bokeh city background, 24fps, cinematic color grading.
Duration: 6–8 seconds. Audio: clear professional male voice, neutral accent, warm and authoritative tone.
Step 4: Generate
Veo 3.1 Fast result — 720p video, loaded only when you choose to play it:
Not perfect. Useable without editing — better with it. The animated GIF format tends to read less obviously as AI-generated content in-feed.
Example 2: Product advertisement
A standard short ad for a bag. Two ingredient photos — the model and the product — plus a structured brief from ChatGPT.
The brief
Rather than a single-line prompt, ask an LLM to produce a full shot list. Upload your two ingredient images, then use this prompt:
See these two images — the model and the product. The product is the feature item. Produce an enterprise-grade 8-second advertisement brief for Veo 3.1 — synced to the model, highlighting the best reason to purchase.
Include:
- Duration, aspect ratios, background, lighting, and camera specs
- Timestamped shot list (0.0–8.0s) with overlay text for each segment
- Negative prompts to prevent common AI artifactsChatGPT’s output for the bag example:
Duration: 8 seconds · Aspect ratios: 1:1, 4:5, 9:16 Background: warm luxury gold gradient · Lighting: sharp specular highlights on gold, soft fill on green stone texture · Camera: macro lens + smooth product dolly
0.0–1.2s — Product Hero: floating bag on gold gradient, slow cinematic push-in, light sweep reveals emerald malachite texture, gold beaded trim, blue gemstones, pearl center medallion. Text overlay: “Handcrafted gemstone detail”
1.2–2.6s — Craftsmanship: ultra-macro cuts (0.3s each) — gold trim, blue stone facet, pearl floral motif, clasp detail. Sound: subtle luxury chime.
2.6–4.2s — Scale + Lifestyle: model enters holding bag at chest height, turns to show structure. Text: “Limited artisan piece”
4.2–6.2s — Desire Shot: model places bag on pedestal, camera locks to symmetrical front view. Light glint across gold trim.
6.2–7.4s — Hero Lockup: static beauty shot, background deepens. Text: “Statement luxury. Small batch.”
7.4–8.0s — CTA: “Own the piece.”
Negative prompts: no fast fashion, no plastic shine, no busy background, no motion blur on product, no warped symmetry, no color shift from emerald/gold/blue/pearl
Results
The retained result from two generations:
Example 3: Text-to-video
No source image needed. Feed a cinematic description directly:
A dimly lit hacker workspace with a glowing ultrawide monitor filled with a terminal UI,
code streaming rapidly. Close-up of hands typing, reflections of green monospace text
in glasses. Smash cut to a clean text prompt on screen: "launch product demo video".
Instantly the screen renders a polished cinematic product clip in a preview window.
Quick over-the-shoulder shot: the developer smirks, hits enter, a progress bar
completes in milliseconds. Final shot: multiple video thumbnails auto-generating
in a grid, terminal text overlay: "text → video → shipped". Subtle camera push-in,
moody lighting, cyberpunk color grading.
Text-to-video is solid for: storyboarding, proofs-of-concept, background footage, b-roll.
Free tier: what you actually get
Credits are shared with Google Whisk — if you use both, budget accordingly (3 Whisk generations = 60 credits, nearly your full daily allowance).
For how Flow fits in the broader free AI stack, see Free Frontier Stack 2026. For a similar breakdown of another Google AI free credit system, see Claude Opus Extra Use: 50 Credits.
Verdict
No perfect videos out of the box. With deliberate prompting and 2–3 takes, you get useable footage.
Works well:
- Animated GIFs for in-feed content (read less obviously as AI-generated)
- Product visualization with good reference images
- Concept clips and storyboarding
- B-roll and background footage
Plan around:
- Garbled text overlays — add readable copy in post
- Occasional anatomy errors (extra limbs, misaligned proportions)
- Quality tier is not accessible on the free plan
- Free credit balance is not shown in the UI — track it yourself
The workflow that gets results: use an LLM to draft a structured brief before you generate. Spend your credits on strong prompts, not random iteration. For a broader look at where AI tools still consistently fall short, see Honest Limitations of AI Tools in 2026.
Related links
- Free Frontier Stack 2026 — Where Flow fits in the free AI toolchain
- Smart Spend Guide — When to upgrade from free tiers
- Honest Limitations of AI Tools in 2026 — What AI still can’t do reliably
- Claude Opus Extra Use: 50 Credits — Another daily-credit free tier breakdown
- Google AI Studio — The developer-facing alternative
- Google Flow — Project page