$ loading_
Give non-multimodal models image descriptions and list available vision models.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "opencode-eyes-nvidia" yet — see the docs or source repo.
Use opencode-eyes-nvidia to describe the main objects, scene, visible text, and overall meaning of this image.
A structured or natural-language image description that helps a non-multimodal model understand the image.
List the vision models currently available through opencode-eyes-nvidia so I can choose one.
A list of available vision models for selecting one in later image description tasks.
In this automation flow, first use opencode-eyes-nvidia to describe the uploaded image, then summarize the key information from that description.
First an image description, then a concise summary of key information for downstream text-model processing.
Developers using non-multimodal models can first convert images into text descriptions with this MCP tool, then pass the result to the model for further analysis or answers.
When an automation flow needs to process images but the main model does not support vision input, this tool can act as an image-understanding layer that provides descriptions.
Teams that need reliable access to NVIDIA vision models can use its multiple NVIDIA API keys with rotation and failover to improve availability.
It is an MCP server that uses NVIDIA NIM's MiniMax-M3 model to generate image descriptions for non-multimodal models, and it can also list available vision models.
Based on the description, you need an NVIDIA API key. It supports multiple keys with automatic failover and rotation; for other installation details, see the source repository.
Its role is to add “vision” to non-multimodal models as an MCP tool, while also offering available vision model listing and high-availability support through multiple NVIDIA keys.
Generate text descriptions from images with fast fallback vision model support.
Let AI read local images for description, OCR, and custom visual analysis.
Lets text-only models analyze and describe images via multimodal APIs.
Let text-only models inspect images via a read_image tool.
Analyze local or remote images with vision LLMs and generate descriptions.
Access NVIDIA-hosted LLM chat, model discovery, and image generation APIs.