Image(s) to Video
Last updated
Last updated
Image-to-Video models generate videos by taking a single image or multiple images as input, using the input image(s) to guide scene continuity, motion, and transitions, resulting in dynamic video content that expands the static visuals into a moving narrative while maintaining visual consistency.
Hailuo Minimax
Powerful, motion-heavy model that generates complex movements and dynamic scenes. Requires longer processing time (~2m).
Complex animations, action scenes, and dynamic video content requiring realistic motion.
/
Kling Pro 1.6
Advanced version with improved motion prediction and spatial coherence. Longer processing time (~5m).
High-quality cinematic sequences and detailed animations.
Duration: 5s, 10s; Aspect Ratio: Auto, Landscape - 16:9 (576x1024),
Portrait - 9:16 (1024x576), Square - 1:1.
Kling Pro 1.5
Slightly more legacy version of Kling Pro with robust temporal consistency but less advanced than 1.6. (~5m).
Smooth motion transitions and consistent scene continuity.
Duration: 5s, 10s; Aspect Ratio: Auto, Landscape - 16:9 (576x1024),
Portrait - 9:16 (1024x576), Square - 1:1.
Luma Dream Machine
Fast processing model (~1m) with a focus on dream-like, surreal visuals and smooth animations.
Abstract animations, surreal video art, and experimental visuals.
Loop: Yes/No.
Pika
Lightweight and faster model (~2m), optimized for simpler animations and basic motion.
Quick animations, social media content, and short video loops.
Frame Rate: 8-24; Camera Motion: 0-100; Guidance Scale(prompt strength on the output): 0-100.
Runway Gen-3 Alpha
State-of-the-art model with advanced generative capabilities and high-quality output. (~40s).
Professional-grade video generation, storytelling, and cinematic experiences.
Aspect Ratio: Landscape - 5:3, Portrait - 3:5; Duration: 5s, 10s.
Lightricks LTXV
Fastest processing (~10s), designed for quick edits and short-form video content.
Social media clips, GIFs, and rapid prototyping of video ideas.
Quality (Increase the quality of the output): 0-100.
These are parameters that are applicable to all our base models.
Prompt
Text
The text prompt is processed through the selected model.
Seed
Seed
The seed is a deterministic number that indexes generations from the model. It's typically randomized, but you can set a seed if there's a particular output you're looking for! Keep in mind that all parameters must be the same in order for a given seed's output to persist.
The Images to Video node generates a video by connecting multiple frames. You can input up to 9 frames and the model will fill in the gaps! It primarily uses IP-Adapter based morphing techniques that's happening in the backend.
You can interact with it in a number of ways:
Input images by clicking the upload button in the node itself
Connect any image output to the node and it'll populate the images section
Reorder or delete images once populated
Use the prompt to help guide the output!
Here are some example workflows using Text to Video in our community page:
