SJinn
SJinn is an AI agent for image and video creation. You can input descriptions to generate images, videos, audio and 3D content. It also provides tool mode, canvas mode and template skills, making it suitable for creative teams that need one-stop material production.
Updated: 2026-10-27
What is SJinn?
SJinn positions itself as a creative agent for image and video creation. The official description is straightforward: describe your creative ideas, and it will generate images, videos, audios, and 3D content. The platform also offers agent mode, tool mode, and canvas mode. Users who prefer manual control can call and fine-tune each feature one by one. Compared with a single generator, it is more like an entrance that integrates multiple generation capabilities into a single workbench, linking a series of operations with a single instruction.
Who is it for?
- Creative professionals who need to quickly produce storyboards, concept maps and short video materials.
- Users who use multiple generation models simultaneously and do not want to switch back and forth between several platforms.
- Developers who want to integrate generation capabilities into their own product processes can use the API and MCP.
- Teams requiring multi-person collaboration or enterprise-level solutions, with corresponding entries available in the official FAQ, and details subject to business communication.
Key features
6Three operation modes
Agent mode automatically advances the entire process based on descriptions, Tool mode is for single-point tool calls, and Canvas mode allows users to arrange and fine-tune images on a canvas.
Multi-type Output
Officially covers images, videos, audio, and 3D content. The same description can be adapted for different media.
Templates and Skills
The platform features entrances to Templates and Skills, allowing users to apply existing styles or load specific skills to constrain the generation direction.
Workspace Management
Workspace aggregates projects and historical generations, making it convenient to continue iterating on the same creative idea in one place without having to re-describe it.
Toolset
Built-in video watermark removal, image-to-video generation, and generation entry points for multiple video models. You can switch horizontally between them within the platform, and the promotional section on the official website also indicates the quota policies for some models.
Interface Integration
Provides API and MCP, allowing you to integrate generation capabilities into your own workflows or enable other agents to call them directly.
How to use SJinn
- 1For beginners, first use the Agent mode to complete a complete creative idea, then switch to the Canvas mode to manually adjust the details and understand what each step does.
- 2The official website banner shows a 40% discount on the annual package. The specific price, quota and promotion period shall be subject to the checkout page.
- 3The free quota and commercial authorization scope are not listed on the homepage. Please read the pricing page and terms of service before official use.
- 4The same description varies significantly across different models. For important projects, generate sample previews first for comparison, then proceed with batch generation.
- 5When handling client materials, first confirm the privacy settings of the project, and the official website's FAQ section specifically addresses whether the project is private.
Traffic & popularity
Data month Sep 2026
SJinn receives about 382.3K visits per month and ranks #84,238 worldwide.
Monthly visits
12 monthsTraffic sources
- Direct58.0%
- Search18.9%
- Social13.3%
- Referrals4.5%
- AI assistants2.7%
- Other2.6%
Top countries
- Brazil15.6%
- United States14.7%
- Japan8.6%
- Germany6.5%
- India4.2%
Estimated from third-party traffic data.
Similar tools
YouArtYouArt is a Chinese AI image and video creation platform that aggregates multiple image and video models. It provides video workflows, 3D director stations, e-commerce and tutorial templates. Some models are available for zero-point trial, making it suitable for creative teams that need to generate a large volume of content.
TrickleTrickle is a canvas-centric AI website building tool that generates web pages, forms, dashboards and interactive pages through natural language, and integrates image and video generation as well as a built-in database, making it suitable for quickly launching ready-to-deploy finished products.
ImagesArt.aiImagesArt is an AI video generator that supports three modes: text-to-video, image-to-video, and first and last frames with reference images. It can output up to 4K resolution with built-in native audio, making it suitable for social media short videos, e-commerce advertisements, and design proposals.
Supawork AIAn AI workspace aggregating multiple models can generate professional avatars, videos and special effects, supports watermark removal, lip syncing and thesis translation, and one subscription covers image, video and learning scenarios.
DezgoDezgo is a multi-model aggregated image and video generation platform. With one interface, you can call models such as Flux, Qwen Image, and Nano Banana. It also provides free tools such as background removal, image upscaling, and redrawing, making it suitable for horizontally comparing image generation effects.
Riverflow 2.0An image generation and editing model for commercial visuals, focusing on the restoration of product details, font control, and style consistency. The official version states that it can correct garbled text in images using reference pictures, and it provides API and MCP access.