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:
For most people looking to generate custom videos from text prompts, we recommend google/veo-3
The Wan video models model by Wan-AI is an excellent open-source option, competitive with the best proprietary video models. Try adjusting the number of steps used for each frame to trade off between generation speed and detail.
Generative video is a rapidly advancing field. Check out the arena and leaderboard at Artificial Analysis to see what's popular today.
Featured models

bytedance/seedance-1-pro-fast
A faster and cheaper version of Seedance 1 Pro
Updated 6 days, 8 hours ago
13.8K runs

google/veo-3-fast
A faster and cheaper version of Google’s Veo 3 video model, with audio
Updated 2 weeks, 6 days ago
107.2K runs
minimax/hailuo-02
Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.
Updated 4 weeks ago
178.1K runs
Recommended Models
The open-source Wan suite (like wavespeedai/wan-2.1-t2v-480p) is among the faster text-to-video options on Replicate, especially at lower resolutions and shorter durations. Many models also have “fast” variants, like google/veo-3-fast, designed for quicker turnaround.
Note: Faster runs usually mean lower resolution or simpler motion.
pixverse/pixverse-v4 offers a strong balance for many use cases. It uses a unit-based system at $0.01 per unit — for example, a 5-second, 360p video costs about $0.30. minimax/hailuo-02 is another good middle-ground option, with both standard and pro modes for different quality levels. Your ideal choice depends on how much resolution and runtime you need and how much you want to spend.
For short, stylized clips (5–10 seconds at lower resolution), pixverse/pixverse-v4 and Wan models are great picks. They’re fast and relatively inexpensive, making them ideal for concept work, storyboarding, or rapid iteration.
If you want high-fidelity motion, longer clips, or more realistic physics, google/veo-3 or minimax/hailuo-02 are better options. minimax/hailuo-02 supports 768p in standard mode and 1080p in Pro mode, which makes it a solid choice for more polished results.
Most text-to-video models generate short video clips (5–10 seconds) at 24 or 30 fps. Supported resolutions range from 360p to 1080p, depending on the model. Some, like google/veo-3, can include audio as part of the output.
Costs vary by model and resolution:
You can push your own model by packaging it with Cog and deploying it. If you’re working with open-source video models, you can also fine-tune them and publish your version for others to use.
Yes, but always check the model’s license. Most text-to-video models on Replicate are available for commercial use, but some authors include additional restrictions.
You can use the Replicate playground or run them programmatically.
Recommended Models

google/veo-3
Sound on: Google’s flagship Veo 3 text to video model, with audio
Updated 1 day ago
192.1K runs


bytedance/seedance-1-pro
A pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution
Updated 1 day, 3 hours ago
882K runs


bytedance/seedance-1-lite
A video generation model that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 720p resolution
Updated 1 day, 3 hours ago
1.5M runs
wan-video/wan-2.5-t2v-fast
Wan 2.5 text-to-video, optimized for speed
Updated 3 days, 3 hours ago
9.3K runs
wan-video/wan-2.5-t2v
Alibaba Wan 2.5 text to video generation model
Updated 3 days, 3 hours ago
13K runs
wan-video/wan-2.5-i2v-fast
Wan 2.5 image-to-video, optimized for speed
Updated 3 days, 3 hours ago
13.8K runs
wan-video/wan-2.5-i2v
Alibaba Wan 2.5 Image to video generation with background audio
Updated 3 days, 3 hours ago
39.4K runs

wavespeedai/wan-2.1-i2v-480p
Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 3 days, 3 hours ago
424.3K runs

wavespeedai/wan-2.1-t2v-720p
Accelerated inference for Wan 2.1 14B text to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 3 days, 3 hours ago
34.9K runs

wavespeedai/wan-2.1-t2v-480p
Accelerated inference for Wan 2.1 14B text to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 3 days, 3 hours ago
179K runs

wavespeedai/wan-2.1-i2v-720p
Accelerated inference for Wan 2.1 14B image to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 3 days, 3 hours ago
85K runs


luma/ray-2-720p
Generate 5s and 9s 720p videos
Updated 1 week ago
29.4K runs


luma/ray
Fast, high quality text-to-video and image-to-video (Also known as Dream Machine)
Updated 1 week ago
58.4K runs

luma/ray-flash-2-540p
Generate 5s and 9s 540p videos, faster and cheaper than Ray 2
Updated 1 week ago
53.9K runs


luma/ray-2-540p
Generate 5s and 9s 540p videos
Updated 1 week ago
10.3K runs


luma/ray-flash-2-720p
Generate 5s and 9s 720p videos, faster and cheaper than Ray 2
Updated 1 week ago
37.5K runs

kwaivgi/kling-v2.5-turbo-pro
Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.
Updated 1 week, 3 days ago
436.9K runs

leonardoai/motion-2.0
Create 5s 480p videos from a text prompt
Updated 3 weeks, 6 days ago
8.5K runs


kwaivgi/kling-v2.1-master
A premium version of Kling v2.1 with superb dynamics and prompt adherence. Generate 1080p 5s and 10s videos from text or an image
Updated 4 weeks, 1 day ago
63.2K runs

pixverse/pixverse-v4
Quickly generate smooth 5s or 8s videos at 540p, 720p or 1080p
Updated 4 weeks, 1 day ago
33K runs

pixverse/pixverse-v4.5
Quickly make 5s or 8s videos at 540p, 720p or 1080p. It has enhanced motion, prompt coherence and handles complex actions well.
Updated 1 month ago
189.3K runs


kwaivgi/kling-v2.1
Use Kling v2.1 to generate 5s and 10s videos in 720p and 1080p resolution from a starting image (image-to-video)
Updated 1 month ago
2.4M runs

pixverse/pixverse-v5
Create 5s-8s videos with enhanced character movement, visual effects, and exclusive 1080p-8s support. Optimized for anime characters and complex actions
Updated 1 month ago
334.3K runs


kwaivgi/kling-v1.6-standard
Generate 5s and 10s videos in 720p resolution at 30fps
Updated 1 month, 1 week ago
1.3M runs


kwaivgi/kling-v2.0
Generate 5s and 10s videos in 720p resolution
Updated 1 month, 1 week ago
78.5K runs

minimax/video-01-director
Generate videos with specific camera movements
Updated 1 month, 2 weeks ago
70.7K runs


kwaivgi/kling-v1.6-pro
Generate 5s and 10s videos in 1080p resolution
Updated 1 month, 2 weeks ago
753.4K runs

wan-video/wan-2.2-i2v-a14b
Image-to-video at 720p and 480p with Wan 2.2 A14B
Updated 2 months, 3 weeks ago
39.8K runs
wan-video/wan-2.2-i2v-fast
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video
Updated 2 months, 3 weeks ago
2.4M runs
wan-video/wan-2.2-t2v-fast
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video
Updated 2 months, 3 weeks ago
105.6K runs

minimax/video-01
Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.
Updated 3 months ago
605K runs

fofr/not-real
Make a very realistic looking real-world AI video
Updated 3 months, 1 week ago
2.2K runs

minimax/video-01-live
An image-to-video (I2V) model specifically trained for Live2D and general animation use cases
Updated 4 months, 1 week ago
169.2K runs

google/veo-2
State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles.
Updated 5 months, 1 week ago
100.8K runs

wan-video/wan-2.1-1.3b
Generate 5s 480p videos. Wan is an advanced and powerful visual generation model developed by Tongyi Lab of Alibaba Group
Updated 8 months ago
43.7K runs


tencent/hunyuan-video
A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions
Updated 9 months ago
114.3K runs


lightricks/ltx-video
LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched.
Updated 9 months, 3 weeks ago
160.6K runs


zsxkib/hunyuan-video2video
A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions
Updated 10 months, 2 weeks ago
2.9K runs


genmoai/mochi-1
Mochi 1 preview is an open video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation
Updated 10 months, 4 weeks ago
3K runs


zsxkib/pyramid-flow
Text-to-Video + Image-to-Video: Pyramid Flow Autoregressive Video Generation method based on Flow Matching
Updated 1 year ago
9K runs


cuuupid/cogvideox-5b
Generate high quality videos from a prompt
Updated 1 year, 2 months ago
2.4K runs


meta/sam-2-video
SAM 2: Segment Anything v2 (for videos)
Updated 1 year, 2 months ago
47K runs


fofr/tooncrafter
Create videos from illustrated input images
Updated 1 year, 3 months ago
61.3K runs


fofr/video-morpher
Generate a video that morphs between subjects, with an optional style
Updated 1 year, 6 months ago
14.9K runs


cjwbw/videocrafter
VideoCrafter2: Text-to-Video and Image-to-Video Generation and Editing
Updated 1 year, 8 months ago
128.8K runs


ali-vilab/i2vgen-xl
RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models
Updated 1 year, 9 months ago
128K runs


open-mmlab/pia
Personalized Image Animator
Updated 1 year, 9 months ago
103.5K runs


zsxkib/animatediff-illusions
Monster Labs' Controlnet QR Code Monster v2 For SD-1.5 on top of AnimateDiff Prompt Travel (Motion Module SD 1.5 v2)
Updated 1 year, 11 months ago
10.5K runs


lucataco/hotshot-xl
😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL
Updated 2 years ago
831K runs


zsxkib/animatediff-prompt-travel
🎨AnimateDiff Prompt Travel🧭 Seamlessly Navigate and Animate Between Text-to-Image Prompts for Dynamic Visual Narratives
Updated 2 years ago
5.7K runs


zsxkib/animate-diff
🎨 AnimateDiff (w/ MotionLoRAs for Panning, Zooming, etc): Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
Updated 2 years ago
58.8K runs

lucataco/animate-diff
Animate Your Personalized Text-to-Image Diffusion Models
Updated 2 years, 1 month ago
317.5K runs


anotherjesse/zeroscope-v2-xl
Zeroscope V2 XL & 576w
Updated 2 years, 3 months ago
298K runs

cjwbw/controlvideo
Training-free Controllable Text-to-Video Generation
Updated 2 years, 5 months ago
2.4K runs

cjwbw/text2video-zero
Text-to-Image Diffusion Models are Zero-Shot Video Generators
Updated 2 years, 6 months ago
42K runs

cjwbw/damo-text-to-video
Multi-stage text-to-video generation
Updated 2 years, 7 months ago
152.7K runs

andreasjansson/tile-morph
Create tileable animations with seamless transitions
Updated 2 years, 8 months ago
529.3K runs


arielreplicate/deoldify_video
Add colours to old video footage.
Updated 2 years, 8 months ago
6.8K runs


pollinations/real-basicvsr-video-superresolution
RealBasicVSR: Investigating Tradeoffs in Real-World Video Super-Resolution
Updated 2 years, 8 months ago
9.2K runs


arielreplicate/robust_video_matting
extract foreground of a video
Updated 2 years, 10 months ago
64.1K runs


arielreplicate/stable_diffusion_infinite_zoom
Use Runway's Stable-diffusion inpainting model to create an infinite loop video
Updated 2 years, 11 months ago
38.4K runs

andreasjansson/stable-diffusion-animation
Animate Stable Diffusion by interpolating between two prompts
Updated 2 years, 11 months ago
119.4K runs

nateraw/stable-diffusion-videos
Generate videos by interpolating the latent space of Stable Diffusion
Updated 3 years, 1 month ago
58.5K runs

deforum/deforum_stable_diffusion
Animating prompts with stable diffusion
Updated 3 years, 1 month ago
265.7K runs