Models tagged "multimodal"

🤖 Model 📝 → 📝

camenduru/minigpt4-video

Analyze and understand video content by generating textual descriptions from video inputs. This model uses interleaved v...

📝 → 📝 • video-analysis • video-understanding • text-generation • 840 runs

🤖 Model 🎥

lucataco/hunyuanvideo-foley

Generate realistic audio from video and text descriptions for professional-grade sound effect creation. Supports high-fi...

🎥 • text-video-to-audio • audio-generation • video-sound-effects • 3 runs

🤖 Model 🖼️

meta/llama-guard-4-12b

Classify text prompts, model responses, and multiple images for safety and policy compliance. Accepts text and a list of...

🖼️ • content-moderation • safety-classification • image-analysis • 15.5K runs

🤖 Model 📝 → 🖼️

fofr/any-comfyui-workflow

Run ComfyUI workflows to generate images or video from a ComfyUI API JSON and optional input media. Accept a workflow JS...

📝 → 🖼️ • comfyui • text-to-image • text-to-video • 6.8M runs