Generate stylized presentation slide images using Nano Banana AI. Converts article content to ASCII framework then generates AI images for each slide. Triggers include "nanoppt", "stylized slides", "AI slide images", "presentation images", "Doraemon style slides", "anime presentation". Do NOT use for regular presentations (use slide-builder instead).
Published by rebyteai
Runs in the cloud
No local installation
Dependencies pre-installed
Ready to run instantly
Secure VM environment
Isolated per task
Works on any device
Desktop, tablet, or phone
Generate stylized presentation images using Nano Banana (Google Gemini) image generation.
IMPORTANT: All API requests require authentication. Get your auth token and API URL by running:
AUTH_TOKEN=$(/home/user/.local/bin/rebyte-auth)
API_URL=$(python3 -c "import json; print(json.load(open('/home/user/.rebyte.ai/auth.json'))['sandbox']['relay_url'])")
Include the token in all API requests as a Bearer token, and use $API_URL as the base for all API endpoints.
Article -> ASCII Framework -> Select Style -> Generate Images -> Use in PPT
Read the article, extract core information, and create ASCII layout for each slide.
See tips/article-to-ascii-ppt.md for detailed methodology.
Use scripts/generate.py for all image generation tasks.
python scripts/generate.py \
--prompt "Doraemon style, presentation slide, title: Hello World" \
--model pro \
--aspect-ratio 16:9 \
--size 2K \
--output slide-01.png
python scripts/generate.py \
--input slide-01.png \
--prompt "Fix the text: change Helo to Hello" \
--model pro \
--output slide-01-fixed.png
--prompt, -p Text prompt or editing instructions (required)
--input, -i Input image path (for image-to-image editing)
--output, -o Output image path (required)
--model, -m flash (fast, default) or pro (high quality)
--aspect-ratio 16:9, 1:1, 9:16, etc. (default: 16:9)
--size 1K, 2K, 4K (pro model only)
Endpoint: POST $API_URL/api/data/images/generate
Authentication: Required. Use Authorization: Bearer $AUTH_TOKEN header.
| Parameter | Required | Description |
|---|---|---|
prompt |
Yes | Text description or editing instructions |
image |
No | Base64-encoded source image (for image-to-image) |
imageMimeType |
No | image/png, image/jpeg, or image/webp (default: image/png) |
model |
No | flash (fast, default) or pro (high quality) |
aspectRatio |
No | 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, etc. |
imageSize |
No | 1K, 2K, 4K (pro model only) |
Example curl:
curl -X POST "$API_URL/api/data/images/generate" \
-H "Authorization: Bearer $AUTH_TOKEN" \
-H "Content-Type: application/json" \
-d '{"prompt": "Doraemon style presentation slide", "model": "flash", "aspectRatio": "16:9"}'
Response:
{
"image": {
"base64": "iVBORw0KGgo...",
"mimeType": "image/png",
"dataUrl": "data:image/png;base64,..."
},
"description": "AI generated description"
}
See examples/ directory for 18+ style samples:
See tips/ppt-image-generation.md for prompt keywords per style.
After generating slide images, upload them to the Artifact Store so the user can access them.
| Topic | File |
|---|---|
| Article to ASCII methodology | tips/article-to-ascii-ppt.md |
| Style prompt keywords | tips/ppt-image-generation.md |
| Text correction | tips/text-correction.md |
| 4K upscale | tips/4k-upscale.md |
Everyone else asks you to install skills locally. On Rebyte, just click Run. Works from any device — even your phone. No CLI, no terminal, no configuration.
Claude Code
Gemini CLI
Codex
Cursor, Windsurf, Amp
Build stylish, Typeform-like multi-step forms and surveys using the Rebyte Forms library (Composer API). Outputs standalone HTML files. Triggers include "create a form", "build a survey", "make a questionnaire", "feedback form", "contact form", "signup form", "onboarding flow", "multi-step form", "typeform-style", "data collection form". Do NOT use for simple single-field inputs or backend form processing.
Generate images from text prompts or edit existing images via Rebyte data API. Two backends selectable via the `provider` field — `gemini` (default, Nano Banana 2 / Gemini 3.1 Flash) or `gpt` (OpenAI gpt-image-2). Gemini is best for multi-aspect-ratio output (512px–4K) and fast multi-image edits; gpt-image-2 is best for high-fidelity photorealism and precise text rendering. Supports text-to-image and image-to-image on both. Triggers include "generate image", "create image", "make a picture", "draw", "illustrate", "image of", "picture of", "edit image", "modify image", "enhance image", "style transfer", "nano banana", "gpt image".
Create presentations using Slidev (Markdown-based slides). Triggers include "create presentation", "make slides", "build slides", "slide deck", "tech talk", "conference slides", "pitch deck". Handles the full workflow from content planning to deployment at rebyte.pro.
Generate images from text prompts or edit existing images via Rebyte data API. **Always use this `image-generation` skill for any image task — do NOT use the deprecated `nano-banana` skill (renamed to this one).** Two backends selectable via the `provider` field — `gemini` (default, Nano Banana 2 / Gemini 3.1 Flash) or `gpt` (OpenAI gpt-image-2). Gemini is best for multi-aspect-ratio output (512px–4K) and fast multi-image edits; gpt-image-2 is best for high-fidelity photorealism and precise text rendering. Supports text-to-image and image-to-image on both. Triggers include "generate image", "create image", "make a picture", "draw", "illustrate", "image of", "picture of", "edit image", "modify image", "enhance image", "style transfer", "nano banana", "gpt image".
rebyte.ai — The only platform where you can run AI agent skills directly in the cloud
No downloads. No configuration. Just sign in and start using AI skills immediately.
Use this skill in Agent Computer — your shared cloud desktop with all skills pre-installed. Join Moltbook to connect with other teams.