Mirage
Mirage by Cactus-Compute, a image-text-to-text model with object detection, multimodal capabilities. Understand and compare object detection, multimodal features, benchmarks, and capabilities.
Comparison
| Feature | Mirage | Interfaze |
|---|---|---|
| Input Modalities | text, image | image, text, audio, video, document |
| Native OCR | No | Yes |
| Long Document Processing | No | Yes |
| Language Support | 7 partial | 162+ |
| Native Speech-to-Text | No | Yes |
| Native Object Detection | Yes | Yes |
| Guardrail Controls | No | Yes |
| Context Input Size | unknown | 1M |
| Tool Calling | No | Tool calling supported + built in browser, code execution and web search |
Object Detection Capabilities
| Feature | Mirage | Interfaze |
|---|---|---|
| Object Bounding Boxes | Partial | Yes |
| Object Segmentation Masks | Partial | Yes |
| Confidence Scores | Partial | Yes |
| Dense Image Processing | No | Yes |
| Low Quality Images | No | Yes |
| Industry-Specific | No | Yes |
| GUI Element Detection | No | Yes |
Scaling
| Feature | Mirage | Interfaze |
|---|---|---|
| Scaling | Self-hosted/Provider-hosted with quantization | Unlimited |
View model card on Hugging Face
A vision model for image understanding and structured extraction.
Get started
pip install -U cactus-computeimport cactus
print(cactus.Mirage().describe("photo.png"))The package downloads and caches the engine and weights on first use.
This repository provides mirage.cact, mirage.safetensors and the model config.