# AI models available in Trending AI Video

The lists below come from the public model picker catalog in the current project release. Runtime routing can affect which entries are selectable on a particular page. Check the live workspace for current availability and the estimated credit cost for your selected settings.

## Video models (13)

- **Seedance 2.5** — High-motion action sequences and expressive character animation. (resolutions: 480p, 720p, 1080p; durations: 4–30 seconds; supports start and end frames; supports reference-to-video input)
- **MiniMax H3 Max** — MiniMax H3 Max video generation with audio. (resolutions: 480P, 768P, 1080P; durations: 5–15 seconds; supports start and end frames)
- **Seedance 2.0** — Stable character preservation and motion coherence. (resolutions: 480p, 720p, 1080p, 4k; durations: 4–15 seconds; supports start and end frames; supports reference-to-video input)
- **Seedance 2.0 Mini** — Faster, lower-cost Seedance generation with native audio and multimodal references. (resolutions: 480p, 720p; durations: 4–15 seconds; supports start and end frames; supports reference-to-video input)
- **MiniMax H3** — Next-generation omni-modal video model with cinematic realism and stereo audio. (resolutions: 768P, 2K; durations: 4–15 seconds; supports start and end frames; supports reference-to-video input)
- **Wan 3.0** — Next-gen video synthesis with fluid temporal consistency and fine detail. (resolutions: 480P, 720P, 1080P; durations: 2–30 seconds; supports start and end frames)
- **Kling 3.0 Turbo** — Ultra-fast and fluid realistic video rendering with intricate motions. (resolutions: 720p, 1080p; durations: 3–15 seconds)
- **Gemini Omni Flash 1.1** — Text and single-image video generation with native audio. (resolutions: 720p, 1080p; durations: 4 seconds, 6 seconds, 8 seconds, 10 seconds)
- **HappyHorse 1.1** — Text or a starting image to video with synchronized audio. (resolutions: 720p, 1080p; durations: 3–15 seconds)
- **FLUX 3 Video** — Text or ordered start and end frames to video with audio. (resolutions: 720p, 1080p; durations: 5–20 seconds; supports start and end frames)
- **LTX-2.5 Fast** — Fast video generation with audio and start/end frames. (resolutions: 720p, 1080p; durations: 6 seconds, 8 seconds, 10 seconds, 12 seconds, 14 seconds, 16 seconds, 18 seconds, 20 seconds; supports start and end frames)
- **Wan 2.7** — High-stability cinematic generative video model. (resolutions: 720P, 1080P; durations: 2–15 seconds; supports start and end frames)
- **Veo 3.1** — Veo 3.1 video generation with audio. (resolutions: 720p, 1080p; durations: 8–8 seconds; supports start and end frames)

## Image models (13)

- **GPT Image 2.5 Flare** — Fast GPT Image 2.5 generation and editing. Resolutions: 1K, 2K, 4K.
- **GPT Image 2.5 Sunburst** — Precision-first GPT Image 2.5 generation and editing. Resolutions: 1K, 2K, 4K.
- **Nano Banana 2.1** — High-fidelity image generation and multi-reference editing with up to 4K output. Resolutions: 1K, 2K, 4K.
- **Seedream 5.0 Pro** — High-definition commercial graphics and clean subject isolation. Resolutions: 1K, 1.5K, 2K.
- **Nano Banana 2** — Fast, high-fidelity daily generation with extraordinary aesthetic coherence. Resolutions: 1K, 2K, 4K.
- **Seedream 5.0 Flash** — Seedream 5.0 Flash image generation. Resolutions: 1K, 1.5K, 2K.
- **Qwen Image 3.0** — Deep semantic understanding across multicultural design styles and typography. Resolutions: 1K, 2K.
- **Grok Imagine Image 2.0** — xAI image generation and reference-image editing. Resolutions: 1K.
- **Nano Banana Pro** — Professional-grade ultra-HD creation with precise reasoning and exceptional fidelity. Resolutions: 1K, 2K, 4K.
- **FLUX.2 Pro** — FLUX.2 Pro image generation. Resolutions: 1K, 2K.
- **Ideogram 4.5** — Accurate typography and image editing at medium quality. Resolutions: 1K.
- **Recraft V4** — Raster images for design and illustration. Resolutions: 1K.
- **Z-Image Turbo** — Z-Image Turbo image generation. Resolutions: 1K.

## Speech and music models (11)

- **ElevenLabs Multilingual** (Speech) — Multilingual text-to-speech.
- **ElevenLabs Turbo 2.5** (Speech) — Fast text-to-speech with ElevenLabs Turbo 2.5.
- **Gemini 3.1 Flash TTS** (Speech) — Gemini Flash text-to-speech.
- **Gemini 2.5 Pro TTS** (Speech) — Gemini Pro text-to-speech.
- **Suno v6** (Music) — Generates full structured songs with high-fidelity vocals, lyrics, and melodies.
- **Suno v6 Wild** (Music) — Creative and experimental Suno generation with richer stylistic variance.
- **Suno v6 Mini** (Music) — Lightweight and fast Suno generation for quick drafts and short tracks.
- **Flow Music** (Music) — Modern beatmaker with adaptable melody loops and chord progressions.
- **ElevenLabs v3** (Speech) — ElevenLabs v3 speech generation.
- **Gemini 3.8 Flash TTS** (Speech) — Gemini 3.8 Flash TTS speech generation.
- **Gemini 3.8 Flash-Lite TTS** (Speech) — Gemini 3.8 Flash-Lite TTS speech generation.

- [Open video model selector](<https://trendingai.video/workspace/ai-video>)
- [Open image model selector](<https://trendingai.video/workspace/ai-image>)
- [Open audio model selector](<https://trendingai.video/workspace/ai-audio>)
- [See plans and credit terms](<https://trendingai.video/pricing>)