Wan2.2 Integrations

Fuser is a browser-based AI creative workspace that lets designers, creative directors, and studios build and run multimodal workflows across text, image, video, audio, 3D, and chatbot/LLM models, all on a single visual canvas. Instead of juggling separate AI tools and subscriptions, Fuser gives you a node-based workflow editor where you can chain models together, iterate on prompts, compare outputs, and ship real creative work with a clear process. Fuser is fully cloud-hosted and runs in the browser—no GPU or local installs. It’s model-agnostic: connect your own API keys from providers like OpenAI, Anthropic, Runway, Fal, and OpenRouter, or use Fuser’s pay-as-you-go credits that never expire. Built for creative and design teams, Fuser is ideal for campaign ideation, product and industrial visualization, motion tests, moodboards, and repeatable content pipelines. Designers can adopt in minutes, not hours, or weeks.

ComfyUI is a free and open source node-based application for generative AI, enabling users to build, create, and share without limits. It allows for the extension of functionality through custom nodes, letting users tailor workflows to their specific needs. Designed for performance, ComfyUI runs workflows directly on local machines, offering faster iteration, lower costs, and complete control. The visual interface provides full control by connecting nodes on a canvas, allowing for branching, remixing, and adjusting every part of the workflow at any time. Workflows can be saved, shared, and reused effortlessly, with exported media carrying metadata to instantly rebuild the full workflow. Users can see results in real-time as they adjust workflows, facilitating faster iteration with instant visual feedback. ComfyUI supports the generation of various media types, including images, videos, 3D assets, and audio.

SiliconFlow is a high-performance, developer-focused AI infrastructure platform offering a unified and scalable solution for running, fine-tuning, and deploying both language and multimodal models. It provides fast, reliable inference across open source and commercial models, thanks to blazing speed, low latency, and high throughput, with flexible options such as serverless endpoints, dedicated compute, or private cloud deployments. Platform capabilities include one-stop inference, fine-tuning pipelines, and reserved GPU access, all delivered via an OpenAI-compatible API and complete with built-in observability, monitoring, and cost-efficient smart scaling. For diffusion-based tasks, SiliconFlow offers the open source OneDiff acceleration library, while its BizyAir runtime supports scalable multimodal workloads. Designed for enterprise-grade stability, it includes features like BYOC (Bring Your Own Cloud), robust security, and real-time metrics.

graphis is a unified creative workspace that empowers designers, marketers, and creators to generate, edit, and enhance images, videos, and text, all within a single intelligent canvas. It eliminates tool-switching by offering a “one canvas for every AI model, every content type, every idea” workflow where users can blend text, visuals, and motion seamlessly. Users can access hundreds of AI models, customize their “AI palette” per project, collaborate in real time, manage versioning and client communication, and automate branding and publishing, all without needing node-based workflow complexity. graphis is designed to replace fragmented toolchains with a single, intuitive platform built by creatives, for creatives, to make AI-powered visual production faster, smarter, and more manageable.

AIReel is an AI-powered video generation platform that enables users to create short-form videos automatically from text prompts or uploaded images without requiring traditional video editing skills. It functions as an all-in-one AI video creator where users simply describe an idea or upload an image, and the system generates a complete video with scenes, motion effects, and music. AIReel relies on multiple advanced generative video models, including engines similar to Sora, Veo, and other multimodal AI systems, to transform text or images into dynamic visual content. Its dual-mode generation system allows both text-to-video and image-to-video workflows, making it possible to animate static photos or generate entirely new cinematic scenes from written prompts. It includes a built-in prompt assistant that helps users refine simple ideas into more detailed instructions so the AI can produce higher-quality results.

Lucy Edit is an open-weight foundation model for text-guided video editing that enables users to apply natural language instructions to videos, no masking, no hand annotations, no external guidance needed. It supports edits such as changing clothing and accessories, replacing characters or objects (e.g., swapping a person with an animal), transforming scenes (style, background, lighting), and making color or style changes, all while preserving the identity of subjects and maintaining motion consistency and realistic appearance across frames. The model is built on the architecture, with a VAE + DiT (diffusion transformer) stack, and designed so that prompts of ~20-30 descriptive words perform best. There’s a free/open version (non-commercial license) plus Pro versions/hosted APIs for more production-oriented use.

Wan AI is a discovery and inspiration hub designed to showcase a curated collection of AI-generated videos and images created by the community, along with the prompts and configurations used to produce them. It allows users to browse a wide range of example outputs, such as cinematic scenes, animations, and stylized visuals, to understand the capabilities of Wan’s models and learn how different prompts, styles, and parameters influence results. Each piece of content is typically paired with its original prompt or input, enabling users to replicate, modify, or build upon existing creations as a starting point for their own projects. This exploration environment plays a key role in the creative workflow by lowering the learning curve, offering practical references for prompt engineering, and helping users quickly identify styles, compositions, and techniques that match their goals.

WaveSpeedAI is a high-performance generative media platform built to dramatically accelerate image, video, and audio creation by combining cutting-edge multimodal models with an ultra-fast inference engine. It supports a wide array of creative workflows, from text-to-video and image-to-video to text-to-image, voice generation, and 3D asset creation, through a unified API designed for scale and speed. The platform integrates top-tier foundation models such as WAN 2.1/2.2, Seedream, FLUX, and HunyuanVideo, and provides streamlined access to a vast model library. Users benefit from blazing-fast generation times, real-time throughput, and enterprise-grade reliability while retaining high-quality output. WaveSpeedAI emphasises “fast, vast, efficient” performance; fast generation of creative assets, access to a wide-ranging set of state-of-the-art models, and cost-efficient execution without sacrificing quality.