AI Models
Explore all AI video and image generation models available on LumiYing. Each model offers unique capabilities — find the perfect one for your project.
Model Catalog
Compare AI video and image models in one workspace
Explore video and image models for text-to-video, reference-led creation, native audio, image editing, and design. Check each model page for its current access status.
Use this catalog when you need to decide between speed, resolution, reference control, native audio, text rendering, and credit efficiency before starting a generation.
- Total
- 25
- Video
- 15
- Image
- 10
Video Models
Generate cinematic AI videos from text, images, and multimodal references.
Seedance 2.5 Flash
Try ad hooks, product shots and social clips faster. Create 4–30 second videos in 480p or 720p with image, video and audio references.
Seedance 2.5
Direct 4–30 second 480p / 720p / 1080p videos with up to 50 multimodal references, more natural human footage, timestamped shots, and storyboard-led control.
Seedance 2.0 Mini
Low-cost Seedance 2.0 family video generation for fast drafts, ad tests, and short-form creative iteration.
Seedance 2.0 Fast
ByteDance's Speed-Optimized 4-Modality Video AI — 2x Faster with Lower Credit Cost
Seedance 2.0
ByteDance's Flagship 4-Modality AI Video Generator with Native Audio
MiniMax H3
Turn ideas and references into product ads and cinematic scenes with native audio.
Gemini Omni 1.2 Flash
Turn product photos and scene ideas into short videos with sound. Edit a clip, connect two frames, or continue the action.
Muse Video
Turn a scene idea or reference photos into a short video with sound.
Kling 4.0
Direct scenes with image, video and audio references. Edit existing footage or extend it from the last frame, with native stereo sound.
Kling 4.0 Flash
Create 720p videos from text, a first frame or visual references. Edit and extend clips with lower credit costs than Kling 4.0.
Kling 3.0
Kuaishou's Director-Style AI Video Model with Native Sound, Keyframes & Motion Control
Kling 3.0 Omni
Kling's Multi-Reference Video Model for Reference Videos, Video Editing & Keyframes
Wan 3.0
Turn photos, clips and sound into scenes worth sharing.
Wan 3.0 Prime
Explore more takes with faster Wan 3.0 video generation.
Grok 1.5
Create short scenes with native sound, image references and up to 720p detail.
Image Models
Create stunning AI images with various styles, resolutions, and reference options.
Seedream 5.5
Create and edit images with up to 10 references, native transparency and 1K–2K output.
GPT Image 2.6
Create product images, animate your references and generate SVG artwork—all in one place.
Nano Banana 2.1
Nano Banana 2.1 is Google’s AI image generation and editing model, with improved visual quality, clearer text, stronger subject consistency, and up to 4K resolution.
GPT Image 2.5
Product scenes, portrait edits and posters, guided by your references
GPT Image 2
GPT-Powered AI Image Generator — Prompt Accuracy, Text Rendering & Reference Editing
Nano Banana 2
Google's Fastest AI Image Generator — Pro Quality at Flash Speed, Up to 4K
Nano Banana Pro
Google's Highest-Quality AI Image Model — 4K, Brand Control & 14 Reference Images
Midjourney
Midjourney's artistic image model in your browser — Stylize control, image references, and 8 aspect ratios, no Discord needed.
Seedream 5.0 Lite
ByteDance's Thinking Image Model — Visual Reasoning, RAG & Style Transfer
Seedream 4.5
4K Image Generation, Typography and Reference Editing
Choosing a Model
How to choose the right LumiYing AI model
The best model depends on the asset you need, the references you already have, and whether you are optimizing for iteration speed or final quality.
Input workflow
Choose text-to-video for fast ideation, image-to-video for character or product consistency, reference video workflows for motion transfer, and image models when the final asset is a still design or concept frame.
Output quality
Use 720p models for drafts and high-volume testing, 1080p models for polished social content, and 4K-capable models when detail, typography, or commercial presentation matters.
Speed and cost
Fast variants are best for rapid iteration because they reduce wait time and credit use. Standard or pro models are better when final quality, native audio, or fine control is more important than speed.
Creative control
For repeatable characters, brand visuals, or structured scenes, prioritize models with multiple references, start/end frames, video editing, or explicit motion-control support.
Start Creating with AI
Choose a model and start generating professional-quality videos and images today.
Try for FreeAI Model FAQ
Quick answers about LumiYing's model catalog and how to choose between video and image generation options.
How many AI models are available on LumiYing?
LumiYing lists 25 model pages covering 15 video models and 10 image models, including Nano Banana 2.1 and the Seedance 2.5 Flash waitlist. Check each page for current availability.
Which LumiYing model should I start with for AI video?
Start with a fast video model when you are testing prompts or social formats, then move to a higher-quality model for final output. If you need character consistency, choose a model that supports image references, start/end frames, or reference video control.
Which LumiYing model should I use for AI images?
Use image models for still assets such as concept art, product visuals, brand images, thumbnails, and design mockups. Choose models with reference-image support when consistency, text rendering, or brand control matters.
Are LumiYing models locked behind specific plans?
No. LumiYing uses a credit-based workspace where supported models are available from the same model catalog. Credits are consumed based on the selected model, workflow, settings, and output requirements.