LLaVA 13B
LLaVA 13B is a vision-language model (VLM) trained on OSS LLM-generated instruction following data. Its state-of-the-art architecture enables seamless interaction between visual content and textual prompts. FireLLaVA supports multi-image and multi-prompt generation. You can seamlessly integrate multiple images into your queries, enhancing context and specificity.
Applications
-
Image Captioning: Generate descriptive captions for images, enriching content across social media, e-commerce, and more.
-
Visual Question Answering (VQA): Pose questions about images, and FireLLaVA provides accurate answers.
-
Creative Writing: Fuel your imagination by combining visual cues with textual prompts
Other Popular Models
sdxl-controlnet
SDXL ControlNet gives unprecedented control over text-to-image generation. SDXL ControlNet models Introduces the concept of conditioning inputs, which provide additional information to guide the image generation process
idm-vton
Best-in-class clothing virtual try on in the wild
fooocus
Fooocus enables high-quality image generation effortlessly, combining the best of Stable Diffusion and Midjourney.
codeformer
CodeFormer is a robust face restoration algorithm for old photos or AI-generated faces.
