|
|
--- |
|
|
license: creativeml-openrail-m |
|
|
pipeline_tag: text-to-image |
|
|
tags: |
|
|
- AIoT |
|
|
- QNN |
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
## Stable-Diffusion-v2.1: Text to Image |
|
|
|
|
|
Stable-Diffusion, developed by Stability AI, is an open-source text-to-image generation model based on the Latent Diffusion architecture, capable of producing high-quality visuals from natural language prompts. Trained on billions of text-image pairs, it generates photorealistic, artistic, or abstract outputs across resolutions (e.g., 512x512 to 1024x1024), widely used in creative design, advertising, game asset development, and educational visualization. The open-source framework enables local deployment with customizable parameters (e.g., prompts, sampling steps) for precise control, while supporting extensions like image inpainting and super-resolution. Challenges include balancing output quality with computational demands (mid-to-high-tier GPUs required), mitigating biased/sensitive content generation, and optimizing real-time performance. |
|
|
|
|
|
The source model can be found [here](https://github.com/CompVis/stable-diffusion/tree/main) |
|
|
|
|
|
## Performance Reference |
|
|
|
|
|
Please search model by model name in [Model Farm](https://aiot.aidlux.com/en/models) |
|
|
|
|
|
## Inference & Model Conversion |
|
|
|
|
|
Please search model by model name in [Model Farm](https://aiot.aidlux.com/en/models) |
|
|
|
|
|
## License |
|
|
|
|
|
- Source Model: [CREATIVEML-OPENRAIL-M](https://github.com/CompVis/stable-diffusion/blob/main/LICENSE) |
|
|
|
|
|
- Deployable Model: [CREATIVEML-OPENRAIL-M](https://github.com/CompVis/stable-diffusion/blob/main/LICENSE) |
