Generate and edit images with Gemini 3 Pro Image at 1K, 2K, or 4K resolutions.
npx skills add https://github.com/unstun/dqn10 --skill inno-figure-gen-unstun
Please help me install this Agent Skill. Skill: inno-figure-gen Source: https://github.com/unstun/dqn10/tree/main/.claude/skills/inno-figure-gen Command: npx skills add https://github.com/unstun/dqn10 --skill inno-figure-gen-unstun
Generate and edit visuals for papers and presentations by leveraging Gemini 3 Pro Image to streamline figure creation.
Run the generation script with a prompt to create a new image or provide --input-image to edit an existing one.
High-intent search queries and answers about installing and using this skill.
You can generate images for academic papers using Gemini Pro AI by running the provided script with a text prompt. The skill processes the request and saves the generated visual directly to a user-specified file path for integration.
Yes, you can edit an existing image for your presentation by providing an input image to the generation script. This image-to-image workflow modifies your current visuals and saves the updated figure to your specified path.
Yes, a Gemini API key is required to use this image generation script. The skill leverages the google-genai dependency to authenticate and process text-to-image and image-to-image generation requests.
Creating figures with Gemini AI supports 1K, 2K, and 4K resolutions. The script auto-detects the correct resolution from your input image when appropriate to maintain visual fidelity for your papers.
The best way to streamline figure creation for academic papers is using an automated script that handles text-to-image and image-to-image workflows. This approach generates and edits visuals at scale, saving outputs directly to your workflow.
Your Gemini image generation script might fail to output 4K resolution figures if the input image lacks sufficient detail for auto-detection or if the API limits restrict the output size for your specific request payload.
resultanyildiziGenerate and edit images via Google's Gemini 3 Pro Image API.
hyperbolic-cGenerate scientific presentation slides and validate readability with OpenRouter Gemini 3 Pro.
refly-aiGenerate and edit images with Gemini 3 Pro Image from text prompts.
alyamenfactoryAccess Gemini-compatible API endpoints via Replit AI Integrations proxy.
