Models tagged "video-to-text"

🤖 Model 🎥

chenxwh/cogvlm2-video

Generate text descriptions and answers from a video input. Accepts a video and an optional prompt to perform video capti...

🎥 • video-to-text • video-auto-captioning • video-question-answering • 663.3K runs

🤖 Model 🎥

uncensored-com/llava-next-video

Answer questions and generate detailed descriptions from a video input. Provide a video and a text prompt to get caption...

🎥 • video-to-text • video-question-answering • 3.6K runs

🤖 Model 🎥

lucataco/apollo-7b

Answer questions about videos and generate detailed captions from a video input. Accepts a video and a natural-language...

🎥 • video-to-text • video-question-answering • 107.0K runs

🤖 Model 🎥

lucataco/videollama3-7b

Generate text descriptions and answers from a video input. Accepts a video and a natural-language prompt to perform vide...

🎥 • video-to-text • video-auto-captioning • 8.2K runs

🤖 Model 🎥

n1jl0091/video-llava-7b-hf_replicate_n1jl0091

Caption videos and answer open-ended questions about their content. Accept one or more video inputs plus a list of natur...

🎥 • video-to-text • video-auto-captioning • video-question-answering • 112 runs

🤖 Model 🖼️ → 📝

lucataco/qwen2-vl-7b-instruct

Caption images and long videos and answer visual questions, returning text. Accepts an image or video plus an instructio...

🖼️ → 📝 • image-to-text • video-to-text • ocr • 259.0K runs

🤖 Model 🎥

aodianyun/qwen2-vl-7b

Caption videos and answer questions about their content. Accepts a video and a natural-language prompt and outputs text...

🎥 • video-to-text • video-auto-captioning • 1.6K runs

🤖 Model 🎥

cuuupid/qwen2-vl-2b

Analyze videos and generate text descriptions, answers, and summaries from a prompt. Accepts a video and an instruction,...

🎥 • video-to-text • video-auto-captioning • 594 runs

🤖 Model 🎥

aodianyun/qwen2-vl-2b

Caption videos. Provide a video and an optional instruction prompt to produce a single text output for captioning, summa...

🎥 • video-to-text • video-auto-captioning • 130 runs

🤖 Model 🎥

sai88uk/minicpm-v-45-v9

Answer questions about images and videos. Accepts an image or a video plus a question and returns text, enabling visual...

🎥 • video-to-text • image-captioning • image-analysis • 1.1K runs

🤖 Model 🖼️ → 📝

lucataco/minicpm-v-4

Caption images and summarize videos from a text prompt, returning natural-language descriptions and answers. Accepts an...

🖼️ → 📝 • image-to-text • video-to-text • ocr • 215 runs

🤖 Model 🎥

jigsawstack/speech-to-text

Transcribe speech to text from audio or video inputs. Auto-detect language or specify one, and optionally translate the...

🎥 • speech-to-text • video-to-text • speaker-diarization • 5 runs

🤖 Model 🎥

tomasruizt/apollo-7b-multiturn

Answer questions about video content in a multi-turn chat. Take a video and a chat message history as input and return a...

🎥 • video-to-text • video-qa • 25 runs

🤖 Model 🖼️ → 📝

aodianyun/minicpm-v-26

Generate text descriptions for images and videos. Accepts an image or video plus an optional prompt and returns text tha...

🖼️ → 📝 • image-to-text • video-to-text • 15 runs

🤖 Model 🖼️ → 📝

hexiaochun/minicpm_v26

Generate captions, answers, and summaries from an input image or video. Accept an image or video plus an optional prompt...

🖼️ → 📝 • image-to-text • video-to-text • 518 runs

🤖 Model 🖼️ → 📝

aodianyun/minicpm-v-26-int4

Caption images and videos from a text prompt, returning textual descriptions and summaries. Accept an image or a video p...

🖼️ → 📝 • image-to-text • video-to-text • 12 runs

🤖 Model 🎥

lucataco/apollo-3b

Caption and answer questions about videos. Takes a video and a text prompt and returns text, enabling detailed descripti...

🎥 • video-to-text • video-question-answering • 142 runs

🤖 Model 🎥

turian/dover-video-quality-assessment

Assess video quality from a video input. Return JSON text with numeric scores for aesthetic appeal, technical quality, a...

🎥 • video-to-text • video-quality-assessment • 28 runs

🤖 Model 📝 → 🔊

lucataco/qwen2.5-omni-7b

Chat and analyze across text, images, audio, and video, returning text responses and optional synthesized speech. Accept...

📝 → 🔊 • text-generation • video-to-text • text-to-speech • 13.9K runs

🤖 Model 🎥

basord/lip-reading-ai-vsr

Transcribe spoken words from silent video using visual speech recognition (lip reading). Input a short clip (2–40 second...

🎥 • video-to-text • lip-reading • 10.1K runs