# Image Gen

AI image generation via Fal.ai, gpt-image-2, nano-banana, MiniMax image-01, and xAI...

- Repository: https://github.com/0xsline/OpenChatCut (2832 stars)
- Category: Media
- License: AGPL-3.0
- Last updated: 2026-10-21
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add 0xsline/OpenChatCut --skill image-gen -g -a claude-code -y`
Codex: `npx skills add 0xsline/OpenChatCut --skill image-gen -g -a codex -y`
Cursor: `npx skills add 0xsline/OpenChatCut --skill image-gen -g -a cursor -y`
Gemini CLI: `npx skills add 0xsline/OpenChatCut --skill image-gen -g -a gemini-cli -y`

## Description

AI image generation via Fal.ai, gpt-image-2, nano-banana, MiniMax image-01, and xAI Grok Imagine. Use when the user wants to generate or create an image / picture / still.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Image Gen

Generate AI images via `submit_image` (configured provider keys only). Prefer one clear still per request unless the user asked for variants.

## Model Selection

| Model | Reference | Strengths | Max refs |
| --- | --- | --- | --- |
| `fal` + `falModel` | [references/fal.md](references/fal.md) | Explicit Fal catalog; see tool schema for per-model limits | Model-specific |
| `gpt-image-2` | [references/gpt-image-2.md](references/gpt-image-2.md) | Best text rendering, strongest prompt adherence | 16 |
| `nano-banana` | [references/nano-banana.md](references/nano-banana.md) | Strongest reference-image fidelity | 14 |
| `image-01` | [references/image-01.md](references/image-01.md) | MiniMax stills / live style; one subject reference via R2 | 1 |
| `grok-imagine` | [references/grok-imagine.md](references/grok-imagine.md) | xAI Grok Imagine; text-to-image, ≤4 outputs, 1K/2K | 0 |

- If Fal.ai is selected or requested, use `model: "fal"` and the requested `falModel` or saved Fal default from capabilities. Ask if none is selected. Native-provider defaults and controls below do not apply to Fal.
- Default: `gpt-image-2` when that key is on.
- Reference-heavy → `nano-banana`.
- User named MiniMax / only MiniMax image key on → `image-01`.
- Respect capabilities: do not call a model whose vendor is not configured.

**IMPORTANT:** Before generating, READ the chosen model's reference.

## Tool Params

The rest: https://github.com/0xsline/OpenChatCut/blob/HEAD/src/agent/skills/image-gen/SKILL.md