Automated summary
Generates and edits images using NVIDIA's FLUX text-to-image and image-editing models via a command-line script.
Strengths
- Simple command-line interface for both generation and editing
- Multiple FLUX models for speed vs quality trade-offs
- Supports configurable aspect ratios, dimensions, and seeds for reproducible results
- Outputs a MEDIA path that chat interfaces can display directly
Limitations
- Requires Python environment with the necessary dependencies and NVIDIA API access
- Limited to the three FLUX models; no support for other image models
- Image editing is text-prompt based only, with no manual masking or region control
When the user needs to generate a new image from a text prompt or edit an existing image using FLUX models.
When the user requires precise image editing (e.g., object removal with masks) or needs a model other than NVIDIA FLUX.
Security analysis
SafeThe skill provides instructions for running Python scripts to generate and edit images via NVIDIA's API. No destructive, obfuscated, or exfiltration actions are present. Commands are straightforward and only involve local execution with user-provided inputs. The embedded API key in the script is a configuration detail and not part of the skill instructions.
No concerns found
How this analysis is madeExamples
Generate a cute cat in spaceMake the background of this image a sunsetGenerate a panoramic beach view in 16:9 aspect rationame: 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
| Model | Use Case | Speed | Quality |
|-------|----------|-------|---------|
| dev | High-quality text-to-image | Normal | Best |
| schnell | Fast text-to-image | Fast | Good |
| kontext | Image editing | Normal | Best |
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)
| Parameter | Short | Default | Description |
|-----------|-------|---------|-------------|
| prompt | | (required) | Text description |
| -o, --output | | output.png | Output file path |
| --width | | 1024 | Output width in pixels |
| --height | | 1024 | Output height in pixels |
| --aspect-ratio | -ar | 1:1 | Aspect ratio preset |
| --steps | -s | 30 | Diffusion steps |
| --seed | | 0 | Random seed (0=random) |
| --model | -m | auto | Model selection |
Image Editing (kontext)
| Parameter | Short | Default | Description |
|-----------|-------|---------|-------------|
| prompt | | (required) | Edit instruction |
| -i, --input | | (required) | Input image path |
| -o, --output | | output.png | Output file path |
| --steps | -s | 30 | Diffusion steps |
| --cfg | | 3.5 | Guidance scale |
| --seed | | 0 | Random seed |
Supported Aspect Ratios
| Ratio | Resolution | |-------|------------| | 1:1 | 1024×1024 | | 16:9 | 1344×768 | | 9:16 | 768×1344 | | 4:3 | 1216×832 | | 3:4 | 832×1216 |
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.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/nvidia-flux-image-generation-msh3uuix/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/nvidia-flux-image-generation-msh3uuix' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/nvidia-flux-image-generation-msh3uuix/download' --output '.skill-downloads/nvidia-flux-image-generation-msh3uuix/SKILL.md.part' && mv '.skill-downloads/nvidia-flux-image-generation-msh3uuix/SKILL.md.part' '.skill-downloads/nvidia-flux-image-generation-msh3uuix/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/nvidia-flux-image-generation-msh3uuix/SKILL.md' && test -s '.skill-downloads/nvidia-flux-image-generation-msh3uuix/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/nvidia-image-gen' && cp -R '.skill-downloads/nvidia-flux-image-generation-msh3uuix' '.claude/skills/nvidia-image-gen'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/nvidia-flux-image-generation-msh3uuix'openskills read 'nvidia-flux-image-generation-msh3uuix'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/nvidia-flux-image-generation-msh3uuix/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.