Models tagged "text-to-video"

🤖 Model 📝 → 🎥

jzhang38/fast-hunyuan-video

Generate videos from text prompts using a fast, distilled HunyuanVideo model. Accepts a text prompt and outputs a silent...

📝 → 🎥 • text-to-video • 465 runs

🤖 Model 📝 → 🎥

lucataco/animate-diff

Generate videos from a text prompt using AnimateDiff motion modules on top of Stable Diffusion checkpoints. Select a mot...

📝 → 🎥 • text-to-video • 316.2K runs

🤖 Model 📝 → 🎥

lucataco/hunyuanvideo

Generate videos from a text prompt. Control resolution (512–1280 width, 320–720 height), duration via 49–129 frames (mus...

📝 → 🎥 • text-to-video • 205 runs

🤖 Model 📝 → 🎥

georgedavila/cog-ltx-video

Generate videos from a text prompt. Control resolution (128–2048), frame count (97–257), and frame rate, with optional s...

📝 → 🎥 • text-to-video • 81 runs

🤖 Model 📝 → 🖼️

fofr/make-someone

Generate images and videos of people based on textual prompts describing their appearance. Create multiple variations of...

📝 → 🖼️ • image-generation • video-generation • text-to-image • 2 runs

🤖 Model 📝 → 🎥

jd7h/open-sora-512

Generate short 512x512 videos from a text prompt. Accepts a prompt (optional seed for reproducibility) and outputs a 16-...

📝 → 🎥 • text-to-video • 566 runs

🤖 Model 📝 → 🎥

camenduru/open-sora

Generate videos from textual prompts, capturing serene and dynamic scenes such as underwater environments with sea turtl...

📝 → 🎥 • text-to-video • video-generation • underwater-scenes • 980 runs

🤖 Model 📝 → 🎥

camenduru/open-sora-plan-512x512

Generate videos from text prompts using the Open Sora Plan model. This model is a work-in-progress and outputs video con...

📝 → 🎥 • text-to-video • video-generation • 1.7K runs

🤖 Model 📝 → 🎥

deepfates/hunyuan-game-of-thrones

Generate Game of Thrones–style videos from a text prompt. Activate the style with the trigger word GMFTH (e.g., “A video...

📝 → 🎥 • text-to-video • video-lora-training • 125 runs

🤖 Model 📝 → 🎥

deforum/deforum_stable_diffusion

Generate videos from text prompts. Animate frames by keyframing prompts over time (e.g., frame: prompt) and controlling...

📝 → 🎥 • text-to-video • 265.6K runs

🤖 Model 📝 → 🎥

andreasjansson/stable-diffusion-animation

Generate looping animations from text by interpolating between a start prompt and an end prompt, outputting GIF or MP4 v...

📝 → 🎥 • text-to-video • prompt-interpolation • 119.4K runs

🤖 Model 📝 → 🎥

deforum-art/deforum-stable-diffusion

Generate animated videos from text prompts, optionally using an init image or a source video. Control 2D and 3D camera m...

📝 → 🎥 • text-to-video • image-to-video • video-to-video • 73.7K runs

🤖 Model 📝 → 🎥

nateraw/stable-diffusion-videos

Generate videos from text prompts by interpolating Stable Diffusion’s latent space. Provide one or more prompts (separat...

📝 → 🎥 • text-to-video • latent-interpolation • 58.5K runs

🤖 Model 📝 → 🎥

arielreplicate/stable_diffusion_infinite_zoom

Generate infinite-zoom loop videos from a text prompt. Create an initial frame with Stable Diffusion, then iteratively i...

📝 → 🎥 • text-to-video • infinite-zoom • 38.4K runs

🤖 Model 📝 → 🎥

camenduru/animate-lcm

Generate 3D animated videos from textual prompts, capturing vivid colors and fantastical themes. Customize video length,...

📝 → 🎥 • text-to-video • 3d-animation • video-generation • 1.3K runs

🤖 Model 📝 → 🎥

zsxkib/animate-diff

Generate short videos from a text prompt with controllable camera motion. Accepts text as input and outputs an mp4 or gi...

📝 → 🎥 • text-to-video • camera-motion • 58.8K runs

🤖 Model 📝 → 🎥

andreasjansson/tile-morph

Generate tileable animations between two text prompts. Interpolate from a start prompt to an end prompt with Stable Diff...

📝 → 🎥 • text-to-video • seamless-tiling • 529.3K runs

🤖 Model 📝 → 🎥

pranavsekhar/compare-image-edit-slideshow

Generate comparison slideshow videos from a text prompt or an optional input image. Automatically create a set of foregr...

📝 → 🎥 • text-to-video • image-to-video • video-slideshow • 1 runs

🤖 Model 📝 → 🎥

adirik/deforum-kandinsky-2-2

Generate animated videos from one or multiple text prompts. Use Kandinsky-2.2 with Deforum pseudo-3D camera motion and a...

📝 → 🎥 • text-to-video • deforum • 7.3K runs

🤖 Model 📝 → 🎥

deepfates/hunyuan-the-lord-of-the-rings

Generate text-prompted videos in the style of The Lord of the Rings. Activate the style with the trigger word THLRD (e.g...

📝 → 🎥 • text-to-video • lord-of-the-rings • 71 runs