Crystallize (Video) turns any video into a faceted, stained-glass mosaic. One radius control lets you dial the crystal size from fine to bold.
Models
All Models
Color Correction (Video) fine-tunes temperature, brightness, contrast, saturation, exposure, shadows, and highlights on any video in one pass.
Chromatic Aberration applies per-channel color shifting to video, creating lens-fringe and glitch effects with independent red, green, and blue controls.
Apply gaussian or kuwahara blur to any video, frame by frame. Control radius and intensity for results ranging from gentle softening to full defocus.
Riverflow 2.0 REFSR by Sourceful fixes blurry or incorrect labels, logos, and packaging text in a scene using reference images as ground truth.
A Scenario text and vision tool powered by leading LLMs. Write, analyze, or reason over text and images. Choose your model, batch up to 5 results.
A timeline-style compositor for Scenario. Stack up to 50 image, video, and audio layers with transforms, blend modes, transitions, and effects.
Compose up to 50 image layers into one output with full control over position, scale, opacity, blend modes, and per-layer effects.
Kling V3 Standard by Kuaishou. Text-to-video with cinematic motion, native audio, and multi-shot storytelling in up to 15-second clips.
Kling V3 I2V Standard by Kuaishou. Animate a start image into cinematic video with optional end frame, native audio, and custom element support.
Kling V3 Pro by Kuaishou. Cinematic text-to-video with multi-shot sequencing, native audio, and per-shot prompt control. Up to 15 seconds per shot.
Gemini 2.5 Flash TTS by Google converts text to natural speech with 30 voice presets and 24 languages, from English to Arabic, Hindi, and Japanese.
Gemini 2.5 Pro TTS by Google converts text to natural speech with 30 voice presets, 24 languages, and expressive style control via text prompt.
Hunyuan 3D 3.1 Pro (Multiview) by Tencent. Turn up to 8 reference views into a textured 3D mesh with up to 1.5M faces and optional PBR materials.
Crystal Video Upscaler by Clarity AI sharpens portraits, faces, and products up to 4K, preserving natural skin texture and identity across frames.
Convert any raster image to a clean, scalable SVG with Recraft. Upload one image and get editable vector paths in seconds.
Stitch 2 to 50 video clips into one, with 18 transition styles, audio control, and export to MP4, MOV, WebM, or GIF.
Detect and crop uniform color borders from images automatically. Set a hex color and tolerance, or let the tool auto-detect from the image corners.
Resize any video to exact pixel dimensions or a maximum file size. Pick how it fits the frame: contain, stretch, or center-crop cover, plus output format, frame rate, and audio control.
Resize images to exact pixel dimensions or a file size cap. Pick how content fits the box: contain to keep the whole image, stretch to fill exactly, or cover to center crop with no distortion.
Regenerate any scene from a new camera angle using Alibaba Qwen Edit 2511 with a multi-angle LoRA. Control azimuth, elevation, and zoom precisely.
Ultrashape 1.0 by PKU-YuanGroup upgrades coarse 3D meshes into high-fidelity, high-poly models using image-guided geometric refinement.
Applies a parabolic warp that curves the sides of any image. Control the bend strength and anchor point for precise, symmetrical distortion effects.
3D Color LUT applies professional color grades to any image using 120+ presets, from film stock emulations to cinematic looks. Adjust intensity for subtle or full effect.
Adds a soft glow and bloom effect to images, with adjustable radius and intensity to enhance bright areas with a cinematic halo.
Dodge & Burn lightens or darkens an image using the classic dodge and burn technique, with eight blend modes (including color and linear) and adjustable intensity.
Reduces color intensity with adjustable strength and four desaturation methods, from subtle muting to full grayscale conversion.
Transforms images into abstract, geometric crystal-fragment compositions. Control polygon region size with the Crystallize Radius slider (1-100).
Fine-tune any image with precise controls for temperature, brightness, contrast, saturation, exposure, shadows, highlights, and gamma.
Adds chromatic aberration to any image by shifting the red, green, and blue channels independently, for a cinematic, lens-distortion effect.
Sparc3D 2.0 Portrait by Hitem3D turns 1 to 4 photos into watertight, PBR-textured 3D head and face meshes optimized for human subjects.
Sparc3D 2.0 by Hitem3D converts 1-4 images into watertight, PBR-textured 3D meshes at up to 1536 Pro resolution, ready for games, AR/VR, or 3D printing.
Qwen Image 2512 by Alibaba generates and transforms images up to 2048px with photorealistic human rendering, native text in images, and support for up to 6 LoRA models.
Seedance 1.5 Pro by ByteDance generates text-to-video and image-to-video clips up to 12 seconds in 1080p, with native audio and multilingual lip-sync.
MM Audio 2 Text-To-Audio (SFX) by Academia / Open Source generates realistic sound effects from text, with clips up to 30 seconds and a guidance strength control.
MM Audio 2 by MMAudio adds synchronized, high-quality audio to silent videos using a text prompt to guide the generated soundscape.
Kling V2.6 Motion Control by Kuaishou transfers motion from a reference video to a character image, replicating body movement, facial expressions, and lip sync.
Qwen Image Layered by Alibaba converts any image into 2 to 8 editable RGBA layers. Each layer is independently movable, resizable, and recolorable.
Flux LoRA for storybook-style isometric backgrounds. Generates warm, detailed fantasy scenes: villages, forests, medieval towns, and architectural environments.
Extend any 16:9 video with Google's Veo 3.1, continuing your clip with visual and audio consistency. Prompt-guided to keep your story flowing.