Wan2.2 Integrations

Fuser is a browser-based, model-agnostic AI workspace for people who actually make things—designers, creative directors, studios, and in-house teams. Most AI tools live at two extremes: one-click toys that spit out a single image, or hardcore toolchains like ComfyUI that assume you have GPUs, config patience, and time. Fuser tries to live in the middle. You get a node-based canvas in your browser where you can wire up text, image, video, audio, 3D, and chatbot/LLM models into multimodal workflows. No local install, no Docker, no drivers. Just open a link and start building. Under the hood, Fuser is provider-agnostic. You can plug in your own API keys from OpenAI, Anthropic, Runway, Fal, OpenRouter, and others, or use Fuser’s own pay-as-you-go credits (which don’t expire). That makes it easier to experiment across models, keep costs visible, and avoid getting locked into a single vendor. The main users are design and creative teams who need to move from brief to concepts quickly: campaign moodboards, product and industrial visualizations, motion tests, content pipelines, and experimental media. Instead of a pile of ad-hoc prompts and screenshots, they get reusable workflows they can share, version, and improve. If you like the power and transparency of node graphs but you’d rather not babysit local installs and drivers, Fuser gives you that orchestration layer as a web app, tuned for people whose job is to ship work, not maintain infra.

ComfyUI is an open-source, free-to-use node-based platform for generative AI that empowers users to create, construct, and share their projects without constraints. It enhances its capabilities through customizable nodes, allowing individuals to adapt their workflows according to their unique requirements. Built for optimal performance, ComfyUI executes workflows directly on personal computers, resulting in quicker iterations, reduced expenses, and total oversight. The intuitive visual interface enables users to manipulate nodes on a canvas, providing the ability to branch, remix, and tweak any aspect of the workflow at any moment. Effortless saving, sharing, and reuse of workflows are possible, with exported media containing metadata for seamless reconstruction of the entire process. Users also benefit from real-time results as they make adjustments to their workflows, promoting rapid iteration coupled with immediate visual feedback. ComfyUI caters to the creation of diverse media formats, such as images, videos, 3D models, and audio files, making it a versatile tool for creators. Overall, its user-friendly design and robust features make it an essential resource for anyone venturing into generative AI.

SiliconFlow is an advanced AI infrastructure platform tailored for developers, providing a comprehensive and scalable environment for executing, optimizing, and deploying both language and multimodal models. With its impressive speed, minimal latency, and high throughput, it ensures swift and dependable inference across various open-source and commercial models while offering versatile options such as serverless endpoints, dedicated computing resources, or private cloud solutions. The platform boasts a wide array of features, including integrated inference capabilities, fine-tuning pipelines, and guaranteed GPU access, all facilitated through an OpenAI-compatible API that comes equipped with built-in monitoring, observability, and intelligent scaling to optimize costs. For tasks that rely on diffusion, SiliconFlow includes the open-source OneDiff acceleration library, and its BizyAir runtime is designed to efficiently handle scalable multimodal workloads. Built with enterprise-level stability in mind, it incorporates essential features such as BYOC (Bring Your Own Cloud), strong security measures, and real-time performance metrics, making it an ideal choice for organizations looking to harness the power of AI effectively. Furthermore, SiliconFlow's user-friendly interface ensures that developers can easily navigate and leverage its capabilities to enhance their projects.

graphis serves as an integrated creative platform that enables designers, marketers, and creators to produce, modify, and improve images, videos, and text within a single smart canvas. By eradicating the need to switch between different tools, it offers a streamlined workflow that combines every AI model, content type, and idea into one cohesive workspace where users can effortlessly merge text, visuals, and motion. The platform provides access to a multitude of AI models, allowing users to tailor their “AI palette” according to specific projects, collaborate in real time, oversee version control and client interactions, and automate branding and publishing processes, all while avoiding the complexities associated with node-based workflows. Built with the creative community in mind, graphis aims to transform disjointed toolsets into a singular, user-friendly platform that enhances the speed, intelligence, and manageability of AI-driven visual production. This innovative approach not only fosters creativity but also ensures that users can focus more on their ideas rather than getting bogged down by technological hurdles.

AIReel is an innovative platform that harnesses artificial intelligence to automatically generate short-form videos from text prompts or uploaded images, eliminating the need for conventional video editing experience. Acting as a comprehensive AI video creator, users can effortlessly convey their ideas or provide images, and the platform generates a polished video complete with scenes, dynamic motion effects, and background music. To achieve this, AIReel utilizes a variety of advanced generative video models, akin to Sora, Veo, and other multimodal AI technologies, which allow for the transformation of both text and images into engaging visual narratives. The platform features a dual-mode generation system that supports both text-to-video and image-to-video processes, enabling the animation of still photographs or the creation of entirely new cinematic sequences from written descriptions. Additionally, AIReel comes equipped with an integrated prompt assistant, which aids users in developing straightforward concepts into comprehensive directives, enhancing the quality of the final output. This combination of features makes AIReel an accessible solution for anyone looking to produce visually appealing content with minimal effort.

Lucy Edit is a versatile foundation model designed for text-driven video editing, allowing users to utilize natural language commands for video modifications without the need for masking, hand annotations, or any external assistance. The model can execute a variety of edits, including alterations to clothing and accessories, character or object replacements, scene transformations encompassing styles, backgrounds, and lighting, as well as adjustments to color and style, all while ensuring that the identity of the subjects is preserved and that motion consistency and realism are maintained throughout the frames. Built on a sophisticated architecture that combines a VAE with a DiT (diffusion transformer) stack, it performs optimally with prompts of approximately 20 to 30 descriptive words. In addition to its free/open version available under a non-commercial license, there are also Pro versions and hosted APIs designed for more intensive production needs. This innovative editing tool represents a significant advancement in the field of video editing, making high-quality modifications accessible to a broader audience.

Wan AI serves as a hub for discovery and inspiration, showcasing a carefully curated selection of AI-generated videos and images contributed by the community, complete with the prompts and configurations utilized in their creation. Users can explore a diverse array of outputs, including cinematic sequences, animations, and unique visuals, which illustrate the capabilities of Wan’s models while also demonstrating how various prompts, styles, and parameters can influence the final results. Each piece of content is generally accompanied by its corresponding prompt or input, allowing users the opportunity to replicate, alter, or enhance existing works as a foundation for their own creative endeavors. This interactive environment significantly aids the creative process by simplifying the learning experience, providing valuable references for prompt engineering, and enabling users to quickly discover styles, compositions, and techniques that align with their artistic aspirations. By fostering a collaborative atmosphere, Wan AI empowers individuals to experiment freely and build upon the community's collective knowledge.

WaveSpeedAI stands out as a powerful generative media platform engineered to significantly enhance the speed of creating images, videos, and audio by leveraging advanced multimodal models paired with an exceptionally quick inference engine. It accommodates a diverse range of creative processes, including transforming text into video, converting images into video, generating images from text, producing voice content, and developing 3D assets, all through a cohesive API built for scalability and rapid performance. The platform integrates leading foundation models such as WAN 2.1/2.2, Seedream, FLUX, and HunyuanVideo, granting users seamless access to an extensive library of models. With its remarkable generation speeds, real-time processing capabilities, and enterprise-level reliability, users enjoy consistently high-quality outcomes. WaveSpeedAI focuses on delivering a “fast, vast, efficient” experience, ensuring quick production of creative assets, access to a comprehensive selection of cutting-edge models, and economical execution that maintains exceptional quality. Additionally, this platform is tailored to meet the demands of modern creators, making it an indispensable tool for anyone looking to elevate their media production capabilities.