Banner maker
A wide banner with deliberate negative space for a headline. Aspect ratio is a
Showcase — Banner maker
A wide banner with deliberate negative space for a headline. Aspect ratio is a
parameter (size for OpenAI, aspect_ratio for Imagen) and it reshapes the
composition more than you'd guess — a scene built for a square is not the scene
built for a 16:9 banner.
Run
bash bootstrap-secrets.sh # reads ../../../../.env, writes secrets/
docker compose up --build # default: PROVIDER=openai
Open http://localhost:3000. Gemini: PROVIDER=gemini docker compose up --build.
What's where
backend/ai_openai.py— widesize="1536x1024"plus a composition hint.backend/ai_gemini.py— Imagen withaspect_ratio="16:9".frontend/app/page.tsx— subject box; renders the banner.
Stop
docker compose down
Run locally
Download the project as a ZIP and run it with Docker. Brings up a FastAPI backend + Next.js frontend on localhost:3000.
unzip banner-maker.zip
cd banner-maker
bash bootstrap-secrets.sh # one-time: pulls API keys into ./secrets
docker compose up --build # default provider: openai
# or: PROVIDER=gemini docker compose up --build
Type some input, pick a provider, and run the same code shown in Source against the live API. Sign-in required.
The same modules the Run button hits. The whole project (frontend, Dockerfile, compose) is in the ZIP under README.
backend/ai_openai.py
"""Showcase 3 (OpenAI): banner maker.
Same generation, a wide aspect ratio and a composition hint that leaves room for
a headline. Aspect ratio is a parameter (`size`), and it changes the result more
than people expect — a scene composed for a square is not the same scene
composed for a banner.
"""
from openai import OpenAI
_client = OpenAI()
_MODEL = "gpt-image-1"
_STYLE = ("A wide website banner illustration: {subject}. Balanced composition "
"with clear negative space on one side for a headline. Modern, clean, "
"high quality.")
def run(subject: str) -> str:
s = subject.strip()
if not s:
return "Describe the banner subject (e.g. 'a mountain sunrise for a travel blog')."
response = _client.images.generate(model=_MODEL, prompt=_STYLE.format(subject=s), size="1536x1024")
return f"data:image/png;base64,{response.data[0].b64_json}"
backend/ai_gemini.py
"""Showcase 3 (Gemini): banner maker via the image model.
Same wide-composition recipe; aspect ratio is expressed in the prompt (the
generate_content image path doesn't take Imagen's aspect_ratio config).
"""
import base64
import os
from google import genai
from google.genai import types
_client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
_MODEL = "gemini-2.5-flash-image"
_STYLE = ("A wide 16:9 website banner illustration: {subject}. Balanced composition "
"with clear negative space on one side for a headline. Modern, clean, "
"high quality.")
def _generate(prompt: str) -> str:
response = _client.models.generate_content(
model=_MODEL, contents=prompt,
config=types.GenerateContentConfig(response_modalities=["TEXT", "IMAGE"]),
)
for part in response.candidates[0].content.parts:
if getattr(part, "inline_data", None) and part.inline_data.data:
b64 = base64.b64encode(part.inline_data.data).decode()
return f"data:image/png;base64,{b64}"
return "No image was generated — try a different subject."
def run(subject: str) -> str:
s = subject.strip()
if not s:
return "Describe the banner subject (e.g. 'a mountain sunrise for a travel blog')."
return _generate(_STYLE.format(subject=s))
Project files
.gitignoreREADME.es.mdREADME.mdbackend/Dockerfilebackend/ai_gemini.pybackend/ai_openai.pybackend/main.pybackend/requirements.txtbootstrap-secrets.shdocker-compose.ymlfrontend/Dockerfilefrontend/app/layout.tsxfrontend/app/page.tsxfrontend/next.config.tsfrontend/package.jsonfrontend/tsconfig.json