%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Longclip SAE ViT L 14
A Long-CLIP model fine-tuned with Sparse Autoencoder (SAE), supporting long-text input and optimized for text-image alignment
Downloads 290
Release Time : 12/19/2024
Model Overview
This model is a fine-tuned version of Long-CLIP ViT-L/14, enhanced with sparse autoencoder technology for improved long-text prompt processing, particularly suitable for use with Tencent Hunyuan Video system
Model Features
Long-text support
Breaks the original CLIP's 77-token limit, effectively handling longer text inputs
Sparse Autoencoder fine-tuning
Optimizes model representation capability through SAE technology, improving text-image alignment
Tencent Hunyuan Video compatibility
Specially optimized for seamless integration with HunyuanVideo system
Adversarial training
Trained on adversarial typographic attack datasets for enhanced robustness
Model Capabilities
Long-text guided image generation
Zero-shot image classification
Cross-modal retrieval
Text-image alignment
Use Cases
Creative content generation
Complex scene image generation
Generates corresponding images from long-text prompts containing multiple details
Can process complex scene descriptions up to 69 tokens
Atypical concept visualization
Transforms abstract or unconventional concepts into visual representations
Maintains excellent consistency and prompt-following capability
Film production assistance
Storyboard design
Generates visual references based on detailed technical descriptions
Accurately understands cinematographic parameters and artistic styles
TransformersFeatured Recommended AI Models