text-to-video AI Models

🤖 Model 📝 → 🎥

minimax/hailuo-2.3

Generate videos from text prompts or a reference image. Supports text-to-video and image-to-video with 6s or 10s clips a...

📝 → 🎥 • text-to-video • image-to-video • 4.0K runs

🤖 Model 📝 → 🎥

pixverse/pixverse-v3.5

Generate 5–8 second videos from a text prompt, with optional background music or sound effects. Optionally start from an...

📝 → 🎥 • text-to-video-with-audio • text-to-video • image-to-video • 2.3K runs

🤖 Model 📝 → 🎥

zsxkib/animatediff-illusions

Generate videos from text prompts with optional ControlNet QR Code guidance. Accept a short control video or GIF as keyf...

📝 → 🎥 • text-to-video • video-to-video • qr-code • 10.5K runs

🤖 Model 📝 → 🎥

zsxkib/animatediff-prompt-travel

Generate videos from text prompts. Animate scenes by changing prompts over time using a prompt_map, with head_prompt, ta...

📝 → 🎥 • text-to-video • 5.7K runs

🤖 Model 📝 → 🎥

lucataco/longcat-video

Generate videos from text prompts with optional image-to-video capabilities. Supports both text-to-video and image-to-vi...

📝 → 🎥 • text-to-video • image-to-video • 153 runs

🤖 Model 📝 → 🖼️

comfyui/any-comfyui-workflow

Execute ComfyUI workflows to generate images or videos from a JSON workflow. Provide an API-format ComfyUI graph plus op...

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

🤖 Model 📝 → 🖼️

ouhenio/stylegan3-clip

Generate human or animal faces from a text prompt as either a single image or a short video. Use CLIP-guided StyleGAN3 t...

📝 → 🖼️ • text-to-image • text-to-video • faces • 6.9K runs

🤖 Model 📝 → 🎥

cjwbw/lavie

Generate short videos from a text prompt. Accepts a prompt and returns a silent video clip (16 frames by default), with...

📝 → 🎥 • text-to-video • 13.9K runs

🤖 Model 📝 → 🎥

fofr/hunyuan-ponponpon

Generate PONPONPON-style animated videos from a text prompt. Include the keyword 'PONPONPON' to trigger the surreal, col...

📝 → 🎥 • text-to-video • ponponpon-style • 140 runs

🤖 Model 📝 → 🎥

fofr/hunyuan-cyberpunk-mod

Generate cyberpunk-themed videos from a text prompt. Activate a photorealistic Cyberpunk 2077 mod aesthetic by including...

📝 → 🎥 • text-to-video • video-lora-training • cyberpunk • 74 runs

🤖 Model 📝 → 🎥

pschaldenbrand/text2video

Generate videos from text prompts. Provide a sequence of text descriptions separated by '&' to animate transitions; the...

📝 → 🎥 • text-to-video • 8.5K runs

🤖 Model 📝 → 🎥

mattrothenberg/dithercam

Generate retro monochrome dithered videos from a text prompt, or animate an input image using a separate video prompt. C...

📝 → 🎥 • text-to-video • image-to-video • dither • 55 runs

🤖 Model 📝 → 🎥

pixverse/pixverse-v4

Generate 5s or 8s videos from a text prompt or a starting image, with optional background music or sound effects. Animat...

📝 → 🎥 • text-to-video • image-to-video • text-to-video-with-audio • 34.6K runs

🤖 Model 📝 → 🎥

jimothyjohn/latentblending

Generate videos from a text prompt. Blend intermediate latents to morph between AI-generated scenes with perceptual simi...

📝 → 🎥 • text-to-video • animation • latent-blending • 1.3K runs

🤖 Model 📝 → 🎥

pollinations/tune-a-video

Generate videos from text prompts by fine-tuning image diffusion models. Transform input videos into new scenes based on...

📝 → 🎥 • text-to-video • video-transformation • image-diffusion • 2.9K runs

🤖 Model 📝 → 🎥

camenduru/magictime

Generate time-lapse videos from textual prompts using metamorphic simulation techniques. Utilize DreamBooth models such...

📝 → 🎥 • text-to-video • time-lapse • video-generation • 369 runs

🤖 Model 📝 → 🎥

zurk/hunyuan-video-8bit

Generate videos from text prompts using an 8-bit optimized version of HunyuanVideo, designed for faster inference on les...

📝 → 🎥 • text-to-video • 242 runs

🤖 Model 📝 → 🎥

cjwbw/show-1

Generate videos from a text prompt. Uses a hybrid pixel- and latent-diffusion pipeline that first creates a low-resoluti...

📝 → 🎥 • text-to-video • 985 runs

🤖 Model 📝 → 🎥

xai/grok-imagine-video

Generates videos with synchronized audio from text prompts or input images using xAI's Grok Imagine Video model. Support...

📝 → 🎥 • text-to-video-with-audio • image-to-video-with-audio • video-editing • 1.2M runs

🤖 Model 📝 → 🎥

runwayml/gen-4.5

Generates videos from text prompts with optional initial image input, achieving precise motion quality and visual fideli...

📝 → 🎥 • text-to-video • image-to-video • 286.8K runs