Business Software for Weavy

Imagen is a text-to-image generation model developed by Google Research. It uses advanced deep learning techniques, primarily leveraging large Transformer-based architectures, to generate high-quality, photorealistic images from natural language descriptions. Imagen's core innovation lies in combining the power of large language models (like those used in Google's NLP research) with the generative capabilities of diffusion models—a class of generative models known for creating images by progressively refining noise into detailed outputs. What sets Imagen apart is its ability to produce highly detailed and coherent images, often capturing fine-grained details and textures based on complex text prompts. It builds on the advancements in image generation made by models like DALL-E, but focuses heavily on semantic understanding and fine detail generation.

Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion. It has a strong understanding of text instructions and can take images and video as input. Ray2 exhibits advanced capabilities as a result of being trained on Luma’s new multi-modal architecture scaled to 10x compute of Ray1. Ray2 marks the beginning of a new generation of video models capable of producing fast coherent motion, ultra-realistic details, and logical event sequences. This increases the success rate of usable generations and makes videos generated by Ray2 substantially more production-ready. Text-to-video generation is available in Ray2 now, with image-to-video, video-to-video, and editing capabilities coming soon. Ray2 brings a whole new level of motion fidelity. Smooth, cinematic, and jaw-dropping, transform your vision into reality. Tell your story with stunning, cinematic visuals. Ray2 lets you craft breathtaking scenes with precise camera movements.

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.

Imagen never stops learning every parameter of your personal editing style. Now you can use your unique point of view easily and quickly on your entire Adobe Lightroom catalogs. Imagen software integrates directly with Adobe Lightroom to apply these styles individually to each photo, and within seconds, achieves a stunning result based on the profile you chose. Through neural networks, Imagen AI takes pre-edited photos, parameters, and metadata from catalogs and generates a profile that is unique to each editor and photographer. AI-driven profiles are fine-tuned and constantly kept accurate, reflecting the evolution of each photographer and editor's unique style. We value your privacy and understand that your materials are yours - and yours only. Your photos or profile will not be shared with anyone without your consent.

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.

Trellis is an AI-driven solution designed to automate and streamline the processing of unstructured data, particularly documents in PDF format. The platform leverages advanced OCR technology to accurately capture text, tables, and handwriting, converting them into usable, structured data. Trellis is built to scale, offering both API integrations and no-code solutions to meet the needs of businesses across various industries. It supports customizable workflows with auto-schema and the ability to define custom actions, enabling users to automate processes and apply specific rules. The platform provides real-time synchronization with source systems, ensuring that the latest data is always available. Trellis also emphasizes data accuracy with flexible validation parameters, allowing users to set their own rules for consistency. Additionally, Trellis ensures robust security through encryption, SOC II Type-2 compliance, and HIPAA-compliant deployment options.

Runway will shepherd your releases from kickoff to submission to release, with no manual intervention. Runway integrates with your favorite tools for a bird’s-eye view over release progress and blockers. Get a rich, contextualized release runbook that makes capturing responsibilities and tracking tasks crystal clear. Surface blockers and get the visibility you need to release confidently and on schedule. Create interactive checklists with clear owners and leave Slack reminders to us. We integrate across your entire toolchain so you can see release status in one browser tab instead of 10. Runway notifies your team of important milestones during your release cycle: release kickoffs, build successes or failures, App Store review statuses, and more. Runway automatically tags your releases and applies missing versions and labels to Jira tickets across projects. Just set up your release cadence and Runway takes care of the rest, from kickoff to release.

This 3D avatar diffusion model is an AI system that automatically produces highly detailed 3D digital avatars. The generated avatars can be freely viewed in 360 degrees with unprecedented quality. The model significantly accelerates traditionally sophisticated 3D modeling process and opens new opportunities for 3D artists. This 3D avatar diffusion model is trained to generate 3D digital avatars represented as neural radiance fields. We build on the state-of-the-art generative technique (diffusion models) for 3D modeling. We use tri-plane representation to factorize the neural radiance field of avatars, which can be explicitly modeled by diffusion models and rendered to images via volumetric rendering. The proposed 3D-aware convolution brings the much-needed computational efficiency while preserving the integrity of diffusion modeling in 3D. The whole generation is a hierarchical process with cascaded diffusion models for multi-scale modeling.

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.

​​Hunyuan T1 is Tencent's deep-thinking AI model, now fully open to all users through the Tencent Yuanbao platform. This model excels in understanding multiple dimensions and potential logical relationships, making it suitable for handling complex tasks. Users can experience various AI models on the platform, including DeepSeek-R1 and Tencent Hunyuan Turbo. The official version of the Tencent Hunyuan T1 model will also be launched soon, providing external API access and other services. Built upon Tencent's Hunyuan large language model, Yuanbao excels in Chinese language understanding, logical reasoning, and task execution. It offers AI-based search, summaries, and writing capabilities, enabling users to analyze documents and engage in prompt-based interactions.

Bria.ai is a powerful generative AI platform that specializes in creating and editing images at scale. It provides developers and enterprises with flexible solutions for AI-driven image generation, editing, and customization. Bria.ai offers APIs, iFrames, and pre-built models that allow users to integrate image creation and editing capabilities into their applications. The platform is designed for businesses seeking to enhance their branding, create marketing content, or automate product shot editing. With fully licensed data and customizable tools, Bria.ai ensures businesses can develop scalable, copyright-safe AI solutions.

Runway Gen-4 is a next-generation AI model that transforms how creators generate consistent media content, from characters and objects to entire scenes and videos. It allows users to create cohesive, stylized visuals that maintain consistent elements across different environments, lighting, and camera angles, all with minimal input. Whether for video production, VFX, or product photography, Gen-4 provides unparalleled control over the creative process. The platform simplifies the creation of production-ready videos, offering dynamic and realistic motion while ensuring subject consistency across scenes, making it a powerful tool for filmmakers and content creators.

​Runway Gen-4 Turbo is an advanced AI video generation model designed for rapid and cost-effective content creation. It can produce a 10-second video in just 30 seconds, significantly faster than its predecessor, which could take up to a couple of minutes for the same duration. This efficiency makes it ideal for creators needing quick iterations and experimentation. Gen-4 Turbo offers enhanced cinematic controls, allowing users to dictate character movements, camera angles, and scene compositions with precision. Additionally, it supports 4K upscaling, providing high-resolution outputs suitable for professional projects. While it excels in generating dynamic scenes and maintaining consistency, some limitations persist in handling intricate motions and complex prompts.

Veo 3 is Google’s latest state-of-the-art video generation model, designed to bring greater realism and creative control to filmmakers and storytellers. With the ability to generate videos in 4K resolution and enhanced with real-world physics and audio, Veo 3 allows creators to craft high-quality video content with unmatched precision. The model’s improved prompt adherence ensures more accurate and consistent responses to user instructions, making the video creation process more intuitive. It also introduces new features that give creators more control over characters, scenes, and transitions, enabling seamless integration of different elements to create dynamic, engaging videos.

FLUX.1 Kontext is a suite of generative flow matching models developed by Black Forest Labs, enabling users to generate and edit images using both text and image prompts. This multimodal approach allows for in-context image generation, facilitating seamless extraction and modification of visual concepts to produce coherent renderings. Unlike traditional text-to-image models, FLUX.1 Kontext unifies instant text-based image editing with text-to-image generation, offering capabilities such as character consistency, context understanding, and local editing. Users can perform targeted modifications on specific elements within an image without affecting the rest, preserve unique styles from reference images, and iteratively refine creations with minimal latency.

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.

Ideogram AI is a text to image AI image generator. Ideogram's technology is based on a new type of neural network called a diffusion model. Diffusion models are trained on a large dataset of images, and they can then generate new images that are similar to the images in the dataset. However, unlike other generative AI models, diffusion models can also be used to generate images in a specific style.