text-to-video AI Models

🤖 Model 📝 → 🎥

fofr/lcm-animation

Generate short animations from text prompts or a starting image. Animate between a start prompt and an end prompt using...

📝 → 🎥 • text-to-video • image-to-video • controlnet • 30.7K runs

🤖 Model 📝 → 🎥

zsxkib/wan-squish

Generate short videos with a squishy, clay-like morphing effect from a text prompt, optionally conditioned on a starting...

📝 → 🎥 • text-to-video • image-to-video • clay-morph • 23 runs

🤖 Model 📝 → 🎥

fofr/wan-14b-cybercab

Generate short videos of a vehicle called CYBERCAB from a text prompt. Optionally start from an input image for image-to...

📝 → 🎥 • text-to-video • image-to-video • taxi • 7 runs

🤖 Model 📝 → 🎥

zsxkib/wan-squish-1000steps

Generate short, stylized videos from a text prompt, with optional image-to-video initialization. Apply an elastic, malle...

📝 → 🎥 • text-to-video • image-to-video • squash-and-stretch • 22 runs

🤖 Model 📝 → 🎥

pipeline-examples/slow-ray

Generate videos from textual prompts using interpolation techniques. This model leverages dependencies like 'luma/ray' a...

📝 → 🎥 • text-to-video • video-generation • interpolation • 2 runs

🤖 Model 📝 → 🎥

wan-video/wan-2.2-t2v-480p-fast

Generate fast and cost-effective videos from text prompts using a highly optimized version of Wan 2.2 A14B. This model s...

📝 → 🎥 • text-to-video • video-generation • fast • 214 runs

🤖 Model 📝 → 🎥

dfischer/tokmeshmetal-4-epoch

Generate videos from a text prompt. Control resolution (up to 1536x1024), frame rate (1–60 fps), duration (up to 1440 fr...

📝 → 🎥 • text-to-video • video-lora-training • 9 runs

🤖 Model 📝 → 🎥

deepfates/hunyuan-westworld

Generate Westworld (2016)-style videos from a text prompt. Use the trigger word WSTWR (e.g., “A video in the style of WS...

📝 → 🎥 • text-to-video • lora • 89 runs

🤖 Model 📝 → 🎥

fofr/wan-14b-black-sclera

Generate short videos with a black-sclera aesthetic from a text prompt or an input image. Produce 1–5 second clips (17–8...

📝 → 🎥 • text-to-video • image-to-video • black-sclera • 29 runs

🤖 Model 📝 → 🎥

chenxwh/nova-t2v

Generate videos from text prompts. Optionally condition on an input image to guide appearance and layout. Control motion...

📝 → 🎥 • text-to-video • image-to-video • 39 runs

🤖 Model 📝 → 🎥

zsxkib/allegro

Generate videos up to 6 seconds at 15 FPS and 720p resolution from text prompts. Supports configurable frame rates up to...

📝 → 🎥 • text-to-video • 144 runs

🤖 Model 📝 → 🎥

chigozienri/animate-diff-sdxl

Generate short videos from a text prompt. Animate SDXL image models with the AnimateDiff motion module (mm_sdxl_v10_beta...

📝 → 🎥 • text-to-video • sdxl • animatediff • 965 runs

🤖 Model 📝 → 🎥

lucataco/hunyuan-heygen-woman-2

Generate short videos of a specific female AI avatar from a text prompt. Maintain consistent character identity using a...

📝 → 🎥 • text-to-video • video-consistent-character-generation • avatar-generation • 253 runs

🤖 Model 📝 → 🎥

ji4chenli/t2v-turbo

Generates videos from text prompts with fast inference speed. Uses the T2V-Turbo (VC2) model architecture optimized for...

📝 → 🎥 • text-to-video • 4.8K runs

🤖 Model 📝 → 🎥

ji4chenli/t2v-turbo-v2

Generate short videos from a text prompt. Configure FPS (8–32), duration via frame count (16–48), denoising steps, guida...

📝 → 🎥 • text-to-video • 617 runs

🤖 Model 📝 → 🎥

pollinations/stable-diffusion-dance

Generate audio-reactive videos by combining visual prompts with audio input. This model creates dynamic visual content t...

📝 → 🎥 • audio-reactive • text-to-video • video-generation • 5.7K runs

🤖 Model 📝 → 🎥

voodoohop/stable-diffusion-dance

Generate audio‑reactive video from text prompts and an input audio file. Provide one or multiple newline‑separated promp...

📝 → 🎥 • text-to-video • audio-to-video • audio-reactive • 21 runs

🤖 Model 📝 → 🎥

google/veo-3.1-fast

Generate videos with synchronized audio from text prompts or images. Start from a still image and optionally specify a l...

📝 → 🎥 • text-to-video-with-audio • image-to-video-with-audio • 524.7K runs

🤖 Model 📝 → 🎥

jzhang38/fast-mochi

Generate videos from a text prompt. Produce silent clips using FastMochi, an accelerated, distilled variant of Mochi, en...

📝 → 🎥 • text-to-video • 60 runs

🤖 Model 📝 → 🎥

bytedance/seedance-1-pro-fast

Generate cinematic videos from a text prompt or a reference image. Optimize for fast, low-cost inference (30–60% faster...

📝 → 🎥 • text-to-video • image-to-video • 65.8K runs