Nvidia Image Gen

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.

Security Scan

The skill appears to implement NVIDIA FLUX image generation as described, but the included script hard-codes an API key and the metadata omits any credential requirement — this mismatch and embedded secret are risky and deserve caution.

Purpose & Capability

The code and SKILL.md align with the stated purpose: it calls NVIDIA FLUX endpoints (ai.api.nvidia.com) and supports text-to-image and image editing modes. Model names and endpoints in the script are consistent with the description. Minor mismatch: registry metadata lists no required env vars, but the script uses and documents an NVIDIA_API_KEY (embedded by default), so the declared requirements understate the credential needs.

Instruction Scope

SKILL.md instructs the agent to run the included Python script with prompt and optional input image; the runtime instructions remain within the image-generation scope. The script will read any input image files you provide, base64-encode them, send them to the Nvidia endpoints, and write output images to disk (MEDIA:/...). It also reads the NVIDIA_API_KEY environment variable if set.

Install Mechanism

There is no install spec (instruction-only), so nothing is downloaded or installed automatically — lower installation risk. The script depends on Python and the 'requests' package but doesn't declare installation steps; runtime errors may occur if dependencies are missing. No external, non-standard download URLs are used by the skill itself.

Credentials

The script embeds a full NVIDIA API key literal and allows override via NVIDIA_API_KEY. The registry metadata declares no required env vars or primary credential — that omission is inconsistent. Hard-coded API keys in distributed code are a security concern (leaked or abused keys, unexpected billing or access). Requiring only the single service key would be proportionate for this skill; embedding one without disclosure is problematic.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or system-wide settings. It writes generated images to the local filesystem (creates output directories), which is expected for an image-generation tool. No elevated persistence or cross-skill configuration changes are present.

What to consider before installing

What to consider before installing: - Embedded API key: The script contains a hard-coded NVIDIA_API_KEY. This is risky — the key may be leaked, revoked, or tied to someone else's account and usage. Prefer a skill that requires you to supply your own API key instead of shipping one in code. If you proceed, replace the embedded key with your own NVIDIA_API_KEY (set in the environment) and remove the literal from the file. - Endpoint verification: The script posts images (base64) to ai.api.nvidia.com. That looks like an official endpoint, but confirm the endpoint and model names with NVIDIA documentation if you need strong assurance. - Data exposure: Any input image you pass will be uploaded to the remote API. Do not pass sensitive images (IDs, documents, private photos) unless you accept that they will be transmitted to the service. - Dependencies & runtime: The script uses Python and the 'requests' library but has no install instructions. Run it in a controlled environment (sandbox or VM) and inspect or run with a non-privileged account. - Replace or revoke keys: If you use the embedded key for testing, monitor usage and revoke it if you detect unexpected activity. Prefer using your own key tied to your account with appropriate quotas. - If you need higher assurance: ask the publisher for provenance (homepage, owner identity, or assurance that the embedded key is intentionally provided for demo/test and not linked to a live billing account). If provenance is not available, treat the skill as untrusted and run only in isolated environments.

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.