Runwayml Stable Diffusion v1.5 OpenVINO
| Property | Value |
|---|---|
| License | CreativeML OpenRAIL-M |
| Framework | OpenVINO |
| Precision | FP16 |
| Task | Text-to-Image Generation |
What is runwayml-stable-diffusion-v1-5-ov?
This is an OpenVINO-optimized version of the popular Stable Diffusion v1.5 model, specifically designed for accelerated inference on Intel CPUs and GPUs. The model has been converted to FP16 precision, reducing its size while maintaining performance capabilities.
Implementation Details
The model leverages OpenVINO's integration with Optimum Intel for efficient deployment. It supports both dynamic and static shapes, with static shapes offering faster inference times. The implementation allows for flexible batch sizes and image dimensions, though larger images require more computational resources.
- FP16 precision optimization for reduced model size
- Compatible with Intel CPU and GPU (11th gen or later)
- Supports static shape optimization for faster inference
- Integrated with Optimum Intel framework
Core Capabilities
- High-quality text-to-image generation
- Optimized performance on Intel hardware
- Configurable image dimensions and batch processing
- Easy integration with just two lines of code
- GPU acceleration support for compatible Intel hardware
Frequently Asked Questions
Q: What makes this model unique?
This model stands out for its OpenVINO optimization, making it specifically tuned for Intel hardware while maintaining the quality of the original Stable Diffusion v1.5. The FP16 precision optimization reduces the model size by half without significant quality loss.
Q: What are the recommended use cases?
The model is ideal for applications requiring text-to-image generation on Intel hardware, particularly where deployment efficiency is crucial. It's especially suitable for systems with Intel GPUs or modern CPUs, and where optimized inference speed is important.
