Generate videos

These models can generate and edit videos from text prompts and images. They use advanced AI techniques like diffusion models and latent space interpolation to create high-quality, controllable video content.

Key capabilities:

  • Text-to-video generation - Convert text prompts into video clips and animations. Useful for quickly prototyping video concepts.
  • Image-to-video generation - Animate still images into video.
  • Inpainting for infinite zoom - Use image inpainting to extrapolate video frames and create infinite zoom effects.
  • Stylization - Apply artistic filters like cartoonification to give videos a unique look and feel.

Our Pick: AnimateDiff

For most people looking to generate custom videos from text or image prompts, we recommend AnimateDiff. This versatile model can animate your own personalized text-to-image diffusion models without requiring specific tuning.

AnimateDiff has quickly become one of the most used models in this collection, with over 150,000 runs. Its ease of use and compatibility with custom models make it a great choice for a wide range of video generation needs.

Also Great: Stable Diffusion Animation

If you want to animate the output of Stable Diffusion models specifically, Stable Diffusion Animation is an excellent option. It works by smoothly interpolating between text prompts to create a video sequence.

With over 100,000 runs, this straightforward approach is popular and effective. It’s a reliable way to bring your Stable Diffusion creations to life.

For Entertaining GIFs: Hotshot-XL

To generate short, high-quality GIFs featuring popular culture figures and styles, try Hotshot-XL. Trained to work alongside Stable Diffusion XL, this model excels at producing fun, shareable GIF content.

Hotshot-XL has been used over 40,000 times, attesting to the appeal of its specialized capabilities. If memes and eye-catching clips are what you’re after, give it a shot.

Recommended models


Zeroscope V2 XL & 576w

263.8K runs


Animating prompts with stable diffusion

243.2K runs


Animate Your Personalized Text-to-Image Diffusion Models

211K runs


Multi-stage text-to-video generation

132.6K runs


Animate Stable Diffusion by interpolating between two prompts

115.8K runs


😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL

108.9K runs


RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

66.3K runs


Generate videos by interpolating the latent space of Stable Diffusion

57.7K runs


extract foreground of a video

44.7K runs


Text-to-Image Diffusion Models are Zero-Shot Video Generators

40.6K runs


🎨 AnimateDiff (w/ MotionLoRAs for Panning, Zooming, etc): Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

39.9K runs


Use Runway's Stable-diffusion inpainting model to create an infinite loop video

35.9K runs


VideoCrafter2: Text-to-Video and Image-to-Video Generation and Editing

17.4K runs


Learning to Animate Images via Latent Space Navigation

17.3K runs


Cartoonifies a video

12.5K runs


Create a video from an image

11.9K runs


Monster Labs' Controlnet QR Code Monster v2 For SD-1.5 on top of AnimateDiff Prompt Travel (Motion Module SD 1.5 v2)

8.6K runs


RealBasicVSR: Investigating Tradeoffs in Real-World Video Super-Resolution

8.6K runs


Audio Reactive Stable Diffusion

5.5K runs


🎨AnimateDiff Prompt Travel🧭 Seamlessly Navigate and Animate Between Text-to-Image Prompts for Dynamic Visual Narratives

5.4K runs


Add colours to old video footage.

4K runs


Hotshot XL using SDXL for generating one second clips of high quality! Running on a40 Made by the greats at and brought to you by your friends at FullJourney! Thanks to LucaTaco for the MVP!

3.9K runs


Text-to-gif using SDXL, with controlnet and lora support

3.3K runs


About Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

2.8K runs


Training-free Controllable Text-to-Video Generation

2K runs