text-generation AI Models

🤖 Model 🖼️ → 📝

sai88uk/minicpm-v-45-v9

Analyzes single images, multiple images, and high-FPS videos to answer questions about their content. Supports controlla...

🖼️ → 📝 • image-to-text • video-to-text • ocr • 14.3K runs

🤖 Model 🖼️ → 📝

lucataco/minicpm-v-4

Analyze images and videos with text prompts to generate detailed text responses. Handles single images, multiple images,...

🖼️ → 📝 • image-to-text • video-to-text • visual-understanding • 795 runs

🤖 Model 🖼️ → 📝

zsxkib/uform-gen

Generates text captions and answers questions about images using a fast 1.5B parameter multimodal language model. Takes...

🖼️ → 📝 • image-to-text • text-generation • image-captioning • 2.4K runs

🤖 Model 🖼️ → 📝

lucataco/fuyu-8b

Generates text responses based on image and text prompts using a multi-modal transformer architecture. Takes an image an...

🖼️ → 📝 • image-to-text • text-generation • 14.7K runs

🤖 Model 🖼️ → 📝

adirik/bunny-phi-2-siglip

Answers questions about images using natural language prompts. Built on SigLIP and Phi-2, this lightweight multimodal mo...

🖼️ → 📝 • image-to-text • text-generation • 7.9K runs

🤖 Model 🖼️ → 📝

lucataco/idefics-8b

Accepts arbitrary sequences of image and text inputs to produce text outputs for multimodal tasks. Answers questions abo...

🖼️ → 📝 • image-to-text • visual-understanding • ocr • 1.2K runs

🤖 Model 🖼️ → 📝

justmalhar/meta-llama-3.2-11b-vision

Analyze images and generate text responses based on visual content and text prompts. Based on Meta's Llama 3.2 11B visio...

🖼️ → 📝 • image-to-text • text-generation • visual-understanding • 312 runs

🤖 Model 🖼️ → 📝

nomagick/qwen-vl-chat

Generates text responses based on text prompts and images with ChatML prompt interface and streaming support. Accepts up...

🖼️ → 📝 • text-generation • image-to-text • image-analysis • 1.1K runs

🤖 Model 🖼️ → 📝

lucataco/sdxl-clip-interrogator

Generates optimized text prompts that match a given image, specifically designed for SDXL image generation models. Takes...

🖼️ → 📝 • image-to-text • text-generation • 848.8K runs

🤖 Model 🖼️ → 📝

lucataco/smolvlm-instruct

Analyzes images and generates text responses based on visual content and text prompts. Accepts arbitrary sequences of im...

🖼️ → 📝 • image-to-text • visual-understanding • document-understanding • 8.3K runs

🤖 Model 🖼️ → 📝

jimothyjohn/phi3-vision-instruct

Analyze images and answer questions about them using text prompts. Built on Microsoft's Phi-3.5-Vision-Instruct, a light...

🖼️ → 📝 • image-to-text • visual-understanding • text-generation • 208 runs

🤖 Model 🖼️ → 📝

zsxkib/molmo-7b

Answers questions and generates captions about images using a 7B parameter vision-language model. Based on Qwen2-7B and...

🖼️ → 📝 • image-to-text • visual-understanding • image-analysis • 1.3M runs

🤖 Model 🖼️ → 📝

jyoung105/honeybee

Analyzes images and generates text responses based on both the image content and text prompts. Uses a locality-enhanced...

🖼️ → 📝 • image-to-text • text-generation • visual-understanding • 30 runs

🤖 Model 🖼️ → 📝

lucataco/gemma-4-31b-it

Generate text responses from text prompts and optional image inputs using Google's open-weight vision-language model. Su...

🖼️ → 📝 • text-generation • image-to-text • visual-understanding • 83 runs

🤖 Model 🖼️ → 📝

lucataco/ollama-llama3.2-vision-90b

Generates text responses based on image and text inputs using Meta's Llama 3.2-Vision 90B multimodal language model. Per...

🖼️ → 📝 • image-to-text • text-generation • visual-understanding • 4.6K runs

🤖 Model 📝 → 📝

2feet6inches/cog-prompt-parrot

Enhances and expands simple Stable Diffusion prompts into more detailed, artistic descriptions. Takes basic text prompts...

📝 → 📝 • text-generation • 36.1K runs

🤖 Model 📝 → 📝

fakturi/bge-reranker-large

Reranks pairs of text queries and documents based on their relevance scores using the BGE reranker large model. Takes JS...

📝 → 📝 • text-embedding • text-generation • 25 runs

🤖 Model 📝 → 📝

lucataco/videollama3-7b

Analyzes videos and generates text descriptions or answers questions about video content. Built on Qwen2.5-7B, this mult...

📝 → 📝 • video-to-text • video-analysis • question-answering • 40.5K runs

🤖 Model 📝 → 📝

tomasruizt/apollo-7b-multiturn

Analyzes videos and engages in multi-turn conversations about video content. Takes a video file and a conversation histo...

📝 → 📝 • video-to-text • text-generation • 25 runs

🤖 Model 📝 → 📝

lucataco/xgen-7b-8k-base

Generates text based on prompts using Salesforce's XGen 7B language model with an 8K context window. Capable of text gen...

📝 → 📝 • text-generation • 115 runs