camenduru/minigpt4-video
Analyze and understand video content by generating textual descriptions from video inputs. This model uses interleaved v...
Found 9 models (showing 1-9)
Analyze and understand video content by generating textual descriptions from video inputs. This model uses interleaved v...
Analyzes videos and generates text descriptions or answers questions about video content. Built on Qwen2.5-7B, this mult...
Generate text descriptions and answers about video content from a video input. Accept a video plus an optional prompt (d...
Evaluates video quality by analyzing both aesthetic appeal and technical quality aspects. Takes a video as input and ret...
Generate text from a video input. Take a video and an instruction prompt, and return captions, summaries, or answers to...
Detect disasters in video. Takes a video input and returns an annotated video highlighting detected disaster events, wit...
Analyzes videos and engages in multi-turn conversations about video content. Takes a video file and a conversation histo...
Analyzes video content and answers questions about it using text prompts. Takes a video file as input and generates text...
Analyzes videos and answers questions about their content through text output. Supports long-form video comprehension in...