Home GenAI Models Stable Diffusion 1.5

Stable Diffusion 1.5

Generate high-quality images from textual descriptions by leveraging advanced deep learning techniques

Model Properties

Uses a Text Encoder to turn prompts into embeddings, an Image Decoder for latent representation, and a UNet Model in 20 steps. Supports batch processing (positive and negative prompts)

License name: CreativeML Open RAIL-M License

Select device..
Hailo-10H

Technical details

Number Of Parameters: 1B
Models Size: 4[GB]

Performance Metrics

Number Of Iterations 20
FPS 0.0625
Sub-Model Performance Metrics
Text Encoder
Input Tokens 77
Number Of Parameters 85.1M
Operations 13.9GOPs
FPS 16
Latency Per Sec 0.533
Image Decoder
Output Resolution [512, 512, 3]
Number Of Parameters 49.5M
Operations 2500GOPs
FPS 0.45
Latency Per Sec 2.222
UNet Model
Number Of Parameters 904.2M
Operations 840.5GOPs
FPS 1.9

Explore Related Models

GenAI Models
Qwen2-VL 2B
Generate multimodal responses by interpreting both text and images, enabling vision-language understanding and content creation
GenAI Models
Qwen2.5-Coder-1.5B-Instruct
Generate text responses to prompts, enabling natural language understanding, multilingual support, and code generation