# AI Video Lab: Generate with 17 Frontier Models | Clip Studio > Direct Seedance 2.5, Veo 3.1 Fast, Kling O3, MiniMax H3 Max, FLUX 3, Wan 3.0 Prime, Kling 3 Pro, and more from one high-end AI video generation workspace. Canonical page: https://clipstudio.ai/video-lab ## Models - [Veo 3.1](https://clipstudio.ai/ai-video-models/veo-3-1.md): A premium text-and-image video model for cinematic shots, guided frames, references, optional audio, and up to 4K output. - [Veo 3.1 Fast](https://clipstudio.ai/ai-video-models/veo-3-1-fast.md): A faster, lower-cost Veo 3.1 SKU for cinematic shots, guided frames, references, optional audio, and up to 4K. - [Seedance 2.5](https://clipstudio.ai/ai-video-models/seedance-2-5.md): A next-generation text-and-image video model with native audio, 30-second shots, first/last frames, and deep reference control. - [Seedance 2.0](https://clipstudio.ai/ai-video-models/seedance-2-0.md): A flexible text-and-image model with first/last-frame direction, up to nine references, broad formats, and optional audio. - [Kling 3 Pro](https://clipstudio.ai/ai-video-models/kling-3-pro.md): A controllable text-and-image model for expressive movement, first/last frames, subject references, and optional audio. - [Kling O3](https://clipstudio.ai/ai-video-models/kling-o3.md): Kling’s newer O3 Standard generation for realistic motion, optional audio, intelligent multi-shot, first-to-last frames, and references. - [Happy Horse 1.1](https://clipstudio.ai/ai-video-models/happy-horse-1-1.md): A native-audio text-and-image model with source-image animation, multi-image references, and broad social formats. - [Gemini Omni Flash](https://clipstudio.ai/ai-video-models/gemini-omni-flash.md): A fast multimodal 1.1 model for text, image animation, first/last frames, and references with native audio up to 4K. - [Wan 3.0](https://clipstudio.ai/ai-video-models/wan-3-0.md): A longer 1080p one-pass text-and-image model with optional native audio, first/last frames, and up to ten references. - [Wan 3.0 Prime](https://clipstudio.ai/ai-video-models/wan-3-0-prime.md): A faster Wan 3.0 SKU for 2–30 second 1080p shots with optional native audio, first/last frames, and up to ten references. - [Wan 2.7](https://clipstudio.ai/ai-video-models/wan-2-7.md): A practical text-and-image generator with first/last frames, multi-image references, 1080p, and repeatable controls. - [MiniMax H3 Max](https://clipstudio.ai/ai-video-models/minimax-h3-max.md): fal’s post-trained MiniMax H3 variant for sub-real-time native-audio clips, image animation, first/last frames, and references at 480p or 768p. - [MiniMax H3](https://clipstudio.ai/ai-video-models/minimax-h3.md): A high-detail native-audio model with first/last frames, references, and 480p through 4K output. - [Grok Imagine Video 1.5](https://clipstudio.ai/ai-video-models/grok-imagine-video-1-5.md): A flexible native-audio model for text, single-image animation, and multi-reference clips from 480p to 1080p. - [FLUX 3](https://clipstudio.ai/ai-video-models/flux-3.md): Black Forest Labs’ frontier video model for text, single-image motion, first-to-last frames, optional native audio, and clips up to 20 seconds. - [PixVerse V6](https://clipstudio.ai/ai-video-models/pixverse-v6.md): A broad text-and-image toolkit with image animation, first/last transitions, four resolutions, and style controls. - [LTX 2.3 Pro](https://clipstudio.ai/ai-video-models/ltx-2-3.md): A production-oriented text-and-image model with first/last frames, 1080p to 4K output, and frame-rate controls. ## FAQs ### What is Clip Studio Video Lab? Video Lab is one workspace for generating videos with text prompts or source images across 17 curated frontier models. Choose a model, add a prompt or image, generate, and keep the completed clip in your Clip Studio Library. ### Are these the 17 most popular AI video models? No objective cross-provider popularity ranking exists. This is an editorial selection of 17 frontier video models chosen for useful differences in quality, speed, control, format support, audio, and resolution. ### How is Video Lab priced? Each plan includes a monthly generation limit. Model, duration, resolution, and other settings use that allowance. Upgrade anytime for a higher monthly limit. ### Can I compare the same prompt across models? Yes. Generate with one model at a time, then use Try another model to preserve your prompt, compatible settings, and available source images while you select a different model. ### Which image-to-video workflows are supported? Every Video Lab model can animate a starting image. Veo, Seedance, Kling, Wan, MiniMax, Gemini, PixVerse, LTX, and FLUX 3 also support first-to-last-frame direction, while Veo, Seedance, Happy Horse, Gemini, Wan, MiniMax H3, MiniMax H3 Max, Kling O3, and Grok offer multi-image reference workflows. Kling 3 Pro uses subject reference elements inside its image workflow.