AI video and image models in Clapova
Clapova gives you dozens of AI models in one subscription. Each guide explains what the model does well, where it falls short, and what one generation costs in credits.
- MiniMax HailuoMiniMax Hailuo is the video engine family from the Chinese lab MiniMax; its current flagship, MiniMax H3 (also called Hailuo 3), launched on July 31, 2026. On Clapova, MiniMax H3 and H3 Max run on the Free plan, with no credit card. Each clip lasts 10 seconds, from a text prompt or a starting image, in 9:16 or 16:9.
- Nano BananaNano Banana is the nickname of Google's Gemini image models. Nano Banana 2 (Gemini 3.1 Flash Image) launched on February 26, 2026 and generates or edits images from a prompt. On Clapova, Nano Banana 2 and its edit mode are included in the Free plan; the original Nano Banana opens at Discovery and Nano Banana Pro at Studio.
- KlingKling is the AI video model family from Kuaishou. Kling 3.0, announced on February 5, 2026, adds native audio, multi-shot storytelling and clips of up to 15 seconds. On Clapova, Kling 3.0 Pro runs text-to-video and image-to-video in 10-second clips on the Studio plan, alongside Kling 2.5 Turbo Pro, Kling 2.1 Pro and Kling 1.0 Standard.
- SeedanceSeedance is ByteDance's AI video model family. Seedance 2.0 launched in February 2026 with joint audio-video generation; Seedance 2.5 followed on July 31, 2026. On Clapova, both run text-to-video and image-to-video with native audio, in 10-second clips at 480p, 720p or 1080p, on the Studio plan. You write the prompt in the Studio, check the price, then edit.
- VeoVeo is Google DeepMind's AI video model family. On Clapova, the Veo model you can use today is Veo 2, announced by Google on December 16, 2024: text-to-video, 8-second clips, no native sound, Studio plan. Veo 3.1 Lite is wired in but only appears when a Google key is set on the server, so Clapova does not offer it by default.
- WanWan is Alibaba's AI video model family. Wan 3.0 became generally available on August 24, 2026 on Alibaba Cloud Model Studio, with clips of up to 30 seconds and inputs mixing text, images, video, audio and documents. On Clapova, Wan 3.0 runs text-to-video and image-to-video in 10-second clips at 480p, 720p or 1080p, on the Studio plan.
- GPT ImageGPT Image is OpenAI's image model line. GPT Image 2, launched on April 21, 2026 as ChatGPT Images 2.0, focuses on text rendering, multilingual text and planned compositions. On Clapova, GPT Image 1.5 opens at the Discovery plan, and GPT Image 2 and its edit mode are reserved for the Studio plan. Neither is free; Nano Banana 2 and Flux are.
- FluxFlux is the model family from Black Forest Labs, the German lab behind FLUX.1 (August 2024), FLUX.2 and FLUX 3 (July 2026). On Clapova, Flux Schnell and Flux Dev are included in the Free plan for fast image drafts; Flux Pro 1.1 Ultra, FLUX 2 and FLUX 3 precise editing open at Creator; FLUX 3 Video, with native audio, needs the Studio plan.