skills$openclaw/nvidia-image-gen
ty-teo1.6k

by ty-teo

nvidia-image-gen – OpenClaw Skill

nvidia-image-gen is an OpenClaw Skills integration for coding workflows. Generate and edit images using NVIDIA FLUX models. Use when user asks to generate images, create pictures, edit photos, or modify existing images with AI. Supports text-to-image generation and image editing with text prompts.

1.6k stars2.5k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026coding

Skill Snapshot

namenvidia-image-gen
descriptionGenerate and edit images using NVIDIA FLUX models. Use when user asks to generate images, create pictures, edit photos, or modify existing images with AI. Supports text-to-image generation and image editing with text prompts. OpenClaw Skills integration.
ownerty-teo
repositoryty-teo/nvidia-image-gen
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @ty-teo/nvidia-image-gen
last updatedFeb 7, 2026

Maintainer

ty-teo

ty-teo

Maintains nvidia-image-gen in the OpenClaw Skills directory.

View GitHub profile
File Explorer
4 files
.
scripts
generate.py
8.8 KB
_meta.json
284 B
SKILL.md
2.8 KB
SKILL.md

name: nvidia-image-gen version: 1.0.0 description: Generate and edit images using NVIDIA FLUX models. Use when user asks to generate images, create pictures, edit photos, or modify existing images with AI. Supports text-to-image generation and image editing with text prompts.

NVIDIA Image Generation

Generate and edit images using NVIDIA's FLUX models.

Models

ModelUse CaseSpeedQuality
devHigh-quality text-to-imageNormalBest
schnellFast text-to-imageFastGood
kontextImage editingNormalBest

Quick Start

# Generate an image
python scripts/generate.py "A cute cat in space"

# Edit an existing image
python scripts/generate.py "Add sunglasses" -i photo.jpg -o edited.png

Parameters

Text-to-Image (dev/schnell)

ParameterShortDefaultDescription
prompt(required)Text description
-o, --outputoutput.pngOutput file path
--width1024Output width in pixels
--height1024Output height in pixels
--aspect-ratio-ar1:1Aspect ratio preset
--steps-s30Diffusion steps
--seed0Random seed (0=random)
--model-mautoModel selection

Image Editing (kontext)

ParameterShortDefaultDescription
prompt(required)Edit instruction
-i, --input(required)Input image path
-o, --outputoutput.pngOutput file path
--steps-s30Diffusion steps
--cfg3.5Guidance scale
--seed0Random seed

Supported Aspect Ratios

RatioResolution
1:11024×1024
16:91344×768
9:16768×1344
4:31216×832
3:4832×1216

Examples

Basic Generation

python scripts/generate.py "A mountain landscape at sunset"

Wide Format (16:9)

python scripts/generate.py "A panoramic beach view" -ar 16:9

Portrait Mode (9:16)

python scripts/generate.py "A professional headshot" -ar 9:16

Custom Size

python scripts/generate.py "A banner image" --width 1344 --height 768

Fast Generation

python scripts/generate.py "Quick sketch of a robot" -m schnell

Edit an Image

python scripts/generate.py "Make the background a sunset" -i input.jpg -o output.png

Reproducible Results

python scripts/generate.py "A robot" --seed 12345

Output

The script outputs MEDIA:/path/to/image.png which can be sent directly to chat.

API Key

The API key is embedded in the script. To use a different key, set the NVIDIA_API_KEY environment variable.

README.md

No README available.

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

  • OpenClaw CLI installed and configured.
  • Language: Markdown
  • License: MIT
  • Topics:

FAQ

How do I install nvidia-image-gen?

Run openclaw add @ty-teo/nvidia-image-gen in your terminal. This installs nvidia-image-gen into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/ty-teo/nvidia-image-gen. Review commits and README documentation before installing.