fal Integrations

AiAssistWorks is the smartest way to use AI in Google Sheets™, Docs™, and Slides™. In Sheets™, just type a simple instruction — and Smart Command uses AI to do the task for you. Instantly generate product descriptions, create formulas, build charts and pivot tables, format data, create tables, validate entries, and more. No formulas. No scripts. No copy-paste. In Docs™, generate, rewrite, translate, create images, and summarize content — all directly inside your document. In Slides™, generate entire presentations or create AI-powered images in just a few clicks. Powered by 100+ AI models including GPT, Claude, Gemini, Llama, Groq, and more — giving you unmatched flexibility. ✅ Free Forever – 100 executions/month with your own API key ✅ Unlimited usage with a paid plan (API key required) ✅ No formulas needed – Fill 1,000+ rows with AI ✅ Automate SEO content, product listings, ad copy, and data labeling in Sheets™, Docs™, and Slides™.

The core of extensible programming is defining functions. Python allows mandatory and optional arguments, keyword arguments, and even arbitrary argument lists. Whether you're new to programming or an experienced developer, it's easy to learn and use Python. Python can be easy to pick up whether you're a first-time programmer or you're experienced with other languages. The following pages are a useful first step to get on your way to writing programs with Python! The community hosts conferences and meetups to collaborate on code, and much more. Python's documentation will help you along the way, and the mailing lists will keep you in touch. The Python Package Index (PyPI) hosts thousands of third-party modules for Python. Both Python's standard library and the community-contributed modules allow for endless possibilities.

Veo 2 is a state-of-the-art video generation model. Veo creates videos with realistic motion and high quality output, up to 4K. Explore different styles and find your own with extensive camera controls. Veo 2 is able to faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles. Significantly improves over other AI video models in terms of detail, realism, and artifact reduction. Veo represents motion to a high degree of accuracy, thanks to its understanding of physics and its ability to follow detailed instructions. Interprets instructions precisely to create a wide range of shot styles, angles, movements – and combinations of all of these.

LTXV offers a suite of AI-powered creative tools designed to empower content creators across various platforms. LTX provides AI-driven video generation capabilities, allowing users to craft detailed video sequences with full control over every stage of production. It leverages Lightricks' proprietary AI models to deliver high-quality, efficient, and user-friendly editing experiences. LTX Video uses a breakthrough called multiscale rendering, starting with fast, low-res passes to capture motion and lighting, then refining with high-res detail. Unlike traditional upscalers, LTXV-13B analyzes motion over time, front-loading the heavy computation to deliver up to 30× faster, high-quality renders.

FLUX.1 is a groundbreaking suite of open-source text-to-image models developed by Black Forest Labs, setting new benchmarks in AI-generated imagery with its 12 billion parameters. It surpasses established models like Midjourney V6, DALL-E 3, and Stable Diffusion 3 Ultra by offering superior image quality, detail, prompt fidelity, and versatility across various styles and scenes. FLUX.1 comes in three variants: Pro for top-tier commercial use, Dev for non-commercial research with efficiency akin to Pro, and Schnell for rapid personal and local development projects under an Apache 2.0 license. Its innovative use of flow matching and rotary positional embeddings allows for efficient and high-quality image synthesis, making FLUX.1 a significant advancement in the domain of AI-driven visual creativity.

Nango is the most comprehensive product integration platform, enabling developers to ship integrations with over 300 APIs in hours. It abstracts away API specificities through pre-built integrations, developer tooling, and UI components. With Nango, you gain full control over the code and access to external APIs, allowing you to build exactly the integrations your customers need as if you were building in-house. The platform offers built-in support for all authorization types and quirks, a single interface with your own data models, and seamless UIs for best-in-class integration experiences. Developer tools are configured per API, handling pagination, rate limits, and more. Nango also provides an AI co-pilot trained on hundreds of integrations to assist in building custom solutions. For those requiring expert assistance, Nango offers access to API experts and an integrations service where Nango engineers build custom integrations for you.

Disco.dev is an open source personal hub for MCP (Model Context Protocol) integration that lets users discover, launch, customize, and remix MCP servers with zero setup, no infrastructure overhead required. It provides plug‑and‑play connectors and a collaborative environment where users can spin up servers instantly via CLI or local execution, explore and remix community‑shared servers, and tailor them to unique workflows. This streamlined, infrastructure‑free approach accelerates AI automation development, democratizes access to agentic tooling, and fosters open collaboration across technical and non-technical contributors through a modular, remixable ecosystem.

Over the last few weeks we all have been overwhelmed by the response and have been working hard to ensure a safe and ethical release, incorporating data from our beta model tests and community for the developers to act on. In cooperation with the tireless legal, ethics and technology teams at HuggingFace and amazing engineers at CoreWeave. We have developed an AI-based Safety Classifier included by default in the overall software package. This understands concepts and other factors in generations to remove outputs that may not be desired by the model user. The parameters of this can be readily adjusted and we welcome input from the community how to improve this. Image generation models are powerful, but still need to improve to understand how to represent what we want better.

Recraft offers the best in class vectorizer that can convert any illustration into a vector with excellent quality and using only a minimal number of points. Browse through the community page to discover new techniques and gain inspiration for beautiful images generation with Recraft. Switch between various artistic styles to transform your images as you need.

MiniMax is an advanced AI company offering a suite of AI-native applications for tasks such as video creation, speech generation, music production, and image manipulation. Their product lineup includes tools like MiniMax Chat for conversational AI, Hailuo AI for video storytelling, MiniMax Audio for lifelike speech creation, and various models for generating music and images. MiniMax aims to democratize AI technology, providing powerful solutions for both businesses and individuals to enhance creativity and productivity. Their self-developed AI models are designed to be cost-efficient and deliver top performance across a variety of use cases.

HunyuanVideo is an advanced AI-powered video generation model developed by Tencent, designed to seamlessly blend virtual and real elements, offering limitless creative possibilities. It delivers cinematic-quality videos with natural movements and precise expressions, capable of transitioning effortlessly between realistic and virtual styles. This technology overcomes the constraints of short dynamic images by presenting complete, fluid actions and rich semantic content, making it ideal for applications in advertising, film production, and other commercial industries.

Orq.ai is the #1 platform for software teams to operate agentic AI systems at scale. Optimize prompts, deploy use cases, and monitor performance, no blind spots, no vibe checks. Experiment with prompts and LLM configurations before moving to production. Evaluate agentic AI systems in offline environments. Roll out GenAI features to specific user groups with guardrails, data privacy safeguards, and advanced RAG pipelines. Visualize all events triggered by agents for fast debugging. Get granular control on cost, latency, and performance. Connect to your favorite AI models, or bring your own. Speed up your workflow with out-of-the-box components built for agentic AI systems. Manage core stages of the LLM app lifecycle in one central platform. Self-hosted or hybrid deployment with SOC 2 and GDPR compliance for enterprise security.

Gemini 2.5 Flash Image is Google’s latest state-of-the-art image generation and editing model, now accessible via the Gemini API, Google AI Studio’s build mode, and Vertex AI. It enables powerful creative control by allowing users to blend multiple input images into a single visual, maintain consistent characters or products across edits for rich storytelling, and apply precise, natural-language-based–based transformations, such as removing objects, changing poses, adjusting colors, or altering backgrounds. The model is backed by Gemini’s deep world knowledge, enabling it to understand and reinterpret scenes or diagrams in context, which unlocks dynamic use cases like educational tutors or scene-aware editing assistants. Demonstrated through customizable template apps in AI Studio (including photo editors, multi-image fusers, and interactive tools), the model supports rapid prototyping and remixing via prompts or UI.

Tavus is an AI-powered platform designed to bring human-like interaction to video conversations. Through its Conversational Video Interface (CVI), Tavus enables AI agents to see, hear, and respond with emotional intelligence, creating a realistic and engaging user experience. Ideal for industries like recruitment, healthcare, and education, Tavus allows businesses to deploy digital twins, AI therapists, and virtual assistants at scale, improving efficiency and user engagement. With Tavus, companies can create fully customizable, human-like video interactions without the limitations of geography, language, or human availability.

Stable Video Diffusion is designed to serve a wide range of video applications in fields such as media, entertainment, education, marketing. It empowers individuals to transform text and image inputs into vivid scenes and elevates concepts into live action, cinematic creations. Stable Video Diffusion is now available for use under a non-commercial community license (the “License”) which can be found here. Stability AI is making Stable Video Diffusion freely available to you, including model code and weights, for research and other non-commercial purposes. Your use of Stable Video Diffusion is subject to the terms of the License, which includes the use and content restrictions found in Stability’s Acceptable Use Policy.

Kling AI is an all-in-one creative studio that empowers filmmakers, artists, and storytellers to turn bold ideas into cinematic visuals. With tools like Motion Brush, Frames, and Elements, creators gain full control over movement, transitions, and scene composition. The platform supports a wide range of styles—from realism to 3D to anime—giving users the freedom to shape projects exactly as they envision. Through the NextGen Initiative, Kling AI also funds and distributes creator projects, with opportunities for global reach and festival exposure. Top creators worldwide use Kling AI to streamline workflows, generate stunning sequences, and experiment with storytelling in ways traditional production can’t match. By combining accessibility, power, and professional-grade results, Kling AI redefines what’s possible for AI-driven creativity.

Nano Banana is the internal codename for Google’s powerful AI image-editing model, officially known as Gemini 2.5 Flash Image. It enables users to transform and refine images using conversational prompts—whether that means colorizing old photos, changing outfits, or merging multiple images into one seamless composition. One of its standout features is preserving character consistency: people, pets, and objects remain recognizable even after multiple edits. It excels at multi-turn editing, meaning you can iteratively tweak the same image and expect coherent results throughout. Nano Banana is integrated into the Gemini app, making these capabilities accessible to both free and paid users. Despite its impressive performance, the images include visible and invisible (SynthID) watermarking to denote AI generation for transparency.

Imagen 3 is the next evolution of Google's cutting-edge text-to-image AI generation technology. Building on the strengths of its predecessors, Imagen 3 offers significant advancements in image fidelity, resolution, and semantic alignment with user prompts. By employing enhanced diffusion models and more sophisticated natural language understanding, it can produce hyper-realistic, high-resolution images with intricate textures, vivid colors, and precise object interactions. Imagen 3 also introduces better handling of complex prompts, including abstract concepts and multi-object scenes, while reducing artifacts and improving coherence. With its powerful capabilities, Imagen 3 is poised to revolutionize creative industries, from advertising and design to gaming and entertainment, by providing artists, developers, and creators with an intuitive tool for visual storytelling and ideation.

Imagen 4 is Google's most advanced image generation model, designed for creativity and photorealism. With improved clarity, sharper image details, and better typography, it allows users to bring their ideas to life faster and more accurately than ever before. It supports photo-realistic generation of landscapes, animals, and people, and offers a diverse range of artistic styles, from abstract to illustration. The new features also include ultra-fast processing, enhanced color rendering, and a mode for up to 10x faster image creation. Imagen 4 can generate images at up to 2K resolution, providing exceptional clarity and detail, making it ideal for both artistic and practical applications.

Hailuo AI represents a pioneering venture into the realm of AI-driven video content creation. This model allows users to generate six-second video clips from textual descriptions, operating at a resolution of 1280x720 with a frame rate of 25 fps. It's designed to democratize video production, enabling creators to visualize their ideas without extensive technical knowledge or equipment. Hailuo AI showcases capabilities in rendering human movement with notable naturalness, alongside handling cinematic camera movements, which sets it apart in the competitive landscape of AI video generators.