Astorie
Astorie is an AI creative canvas for creators and teams, designed to bring image, video, audio, 3D, and multi-model workflows into one connected workspace. Users can generate images with models such as Nano Banana, FLUX, GPT Image, and Grok, compare outputs side by side, and turn prompts, images, or voices into video using models including Seedance, Kling, Veo, Runway, and Sora. Its node-based canvas lets creators connect models and tools into reusable pipelines instead of generating isolated assets. Video workflows support image-to-video, text-to-video, multi-shot sequences, character consistency, lip sync, avatars, talking heads, product videos, ad creatives, and video-to-video transformation. Built-in editing tools enable upscaling, restyling, inpainting, extending, background removal, and other refinements without leaving the canvas.
Learn more
HappyHorse 1.1
HappyHorse-1.1-T2V is a text-to-video generation model available through QwenCloud. The model turns text prompts into video output with improved semantic understanding, cinematic shot control, and dynamic motion rendering. HappyHorse-1.1-T2V is designed to capture creative intent more accurately while producing videos with smoother motion, richer details, and stronger visual consistency. It supports natural character actions, scene atmosphere, and physical dynamics for more realistic video generation. The model can be accessed through the QwenCloud API with configurable options such as resolution, aspect ratio, and duration. Built for developers, creators, and AI product teams, HappyHorse-1.1-T2V helps generate high-quality videos from text prompts at scale.
Learn more
SparkVid
SparkVid is an AI video maker that turns text prompts, photos, product shots, and artwork into cinematic videos using leading generation models in one browser-based workspace. Users can switch between models such as Seedance, Kling, Veo, Sora, MiniMax, and Grok to compare results and choose the take that best fits the project. It reads the scene, camera movement, lighting, and style while helping keep faces, products, and visual identities consistent from the first frame to the last. Motion Control lets creators transfer movement from a reference video, direct pans, zooms, orbits, and dolly shots, and animate faces and body language with greater control. AI video editing makes it possible to remove objects, replace backgrounds, or restyle footage by simply describing the desired change, without masks or keyframes. SparkVid also includes AI image generation for creating concept art, product shots, characters, and thumbnails with models such as GPT Image and Nano Banana.
Learn more
Lucent
Lucent Chat is a unified AI creative workspace that lets you generate and iterate video, image, and ad creatives simply by chatting, no tool-switching or prompt-engineering required. It combines over 20 top generative-AI models (such as Veo, Sora, Seedream, Nano Banana) into one seamless interface, automatically selecting and optimizing the right model for your request behind the scenes. You start by describing what you want, and Lucent handles everything: scripting, scene planning, voice/avatars, model parameters, style tuning, and output export. The platform supports rapid iteration (change the hook, scene, or voice and regenerate variants in seconds), side‐by‐side comparisons of results, and branded workspaces so teams can maintain a consistent visual identity. It’s geared toward creators and marketers who want to produce campaign-ready video ads, social visuals, or creative experiments at scale.
Learn more
