ComfyUI Integrations

Image MetaHub is a local-first, open-source desktop app for managing AI-generated images and videos. It automatically reads generation metadata from tools such as ComfyUI, Automatic1111, Forge, Fooocus, InvokeAI, SwarmUI, SD.Next and Draw Things, making it easier to search, compare, organize and continue previous generations. Users can browse large local libraries, inspect prompts, models, LoRAs, seeds, samplers, steps and workflows, compare variations side by side, add tags and notes, preserve PNG metadata on export, and send images or prompts back into supported generation tools for further work. Image MetaHub is designed for creators who want full control of their media library without uploading files to the cloud, keeping their AI outputs, workflows and metadata private and accessible on their own machine.

Hi3D is an AI-powered 3D generation platform that transforms images into high-quality, production-ready 3D models for creators, designers, engineers, and 3D printing professionals. Built on the Sparc3D × Ultra3D engine, the platform focuses on generating clean geometry, preserving sharp edges, reconstructing hidden surfaces, and delivering realistic textures suitable for professional workflows. Users can upload a single image or multiple views and generate detailed 3D assets with accurate structure, human-like realism, and high-resolution PBR textures. Hi3D supports a wide range of use cases including 3D printing, game design, animation, film production, architecture, sculpture, fashion, jewelry design, and product visualization. The platform includes specialized features such as AI texturing, 3D relief generation, multi-color model segmentation for 3D printing, portrait-focused 3D reconstruction, and de-lighted texture generation.

Count on GridMarkets to ensure your project is delivered on time. Our rendering & simulation service includes 100s of powerful CPUs & GPUs, flexible price plans, and scale options to fit every budget and timeline. Easily set up and submit from your DCC software to our render farm using Envoy, our secure render manager. GridMarkets supplies the software licenses needed to run your render or simulation at scale. No local licenses are needed for the submission process. GridMarkets credits are needed to pay for our rendering and simulation services. A positive GridMarkets credit balance is needed to render or simulate. We also offer a managed services option, whereby a member of the GridMarkets team joins yours to help to prepare and optimize your scene for submission within your budget and timeline.

Database Mart offers a comprehensive suite of server hosting solutions tailored for diverse computing needs. Their VPS hosting provides isolated CPU, memory, and disk resources with full root or admin access, supporting various applications such as database hosting, mail servers, file sharing, SEO tools, and script testing. These VPS plans come with SSD storage, automated backups, and an intuitive control panel, making them ideal for individuals and small businesses seeking cost-effective solutions. For more demanding applications, Database Mart's dedicated servers offer exclusive resources, ensuring superior performance and security. These servers are customizable to support large software systems and high-traffic e-commerce platforms, providing reliability for critical operations. Their GPU servers feature high-performance NVIDIA GPUs, catering to high-performance computing and advanced AI workloads.

Thunder Compute is a GPU cloud platform built for teams searching for cheap cloud GPUs without sacrificing performance, reliability, or ease of use. Developers, startups, and enterprises use Thunder Compute to launch H100, A100, and RTX A6000 GPU instances for AI training, LLM inference, fine-tuning, deep learning, PyTorch, CUDA, ComfyUI, Stable Diffusion, batch inference, and high-performance GPU workloads. With fast GPU provisioning, transparent pricing, persistent storage, and simple deployment, Thunder Compute makes cloud GPU hosting more accessible and cost-effective than traditional hyperscalers. Whether you need affordable GPUs for machine learning, a GPU server for AI, or a low-cost alternative to expensive GPU cloud providers, Thunder Compute helps you scale quickly with reliable on-demand GPU infrastructure designed for modern AI workloads. Thunder Compute is ideal for startups, ML engineers, and research teams that want cheap cloud GPUs with fast setup and predictable costs.

Qwen-Image is a multimodal diffusion transformer (MMDiT) foundation model offering state-of-the-art image generation, text rendering, editing, and understanding. It excels at complex text integration, seamlessly embedding alphabetic and logographic scripts into visuals with typographic fidelity, and supports diverse artistic styles from photorealism to impressionism, anime, and minimalist design. Beyond creation, it enables advanced image editing operations such as style transfer, object insertion or removal, detail enhancement, in-image text editing, and human pose manipulation through intuitive prompts. Its built-in vision understanding tasks, including object detection, semantic segmentation, depth and edge estimation, novel view synthesis, and super-resolution, extend its capabilities into intelligent visual comprehension. Qwen-Image is accessible via popular libraries like Hugging Face Diffusers and integrates prompt-enhancement tools for multilingual support.

Comfy Cloud delivers the full functionality of ComfyUI, a node-based visual generative-AI workflow engine, directly in the browser with no setup required. It works anywhere instantly, giving users access to the most powerful server GPUs (such as A100/40 GB) while maintaining stability and performance. All popular open and closed source models (e.g., Stable Diffusion 1.5/SDXL, Qwen-Image, ByteDance SeeDream4.0, Ideogram, Moonvalley) and pre-installed custom nodes are ready to use, while the platform is kept continuously up to date and the underlying infrastructure is managed for you. Users pay only for GPU runtime, not idle time, so editing, setup, and downtime aren’t billed. It supports browser-based creation on any device, handles workflows at scale, and simplifies team deployment with enterprise-grade features such as priority queuing, dedicated resources, and organizational plans.

Floyo is a browser-based platform that brings the full power of ComfyUI into the cloud, letting users find, launch, and run open source AI workflows in seconds with zero installation, zero idle costs, and no complex setup or missing dependencies to manage, so creators can focus on output rather than infrastructure. It offers free unlimited workflow building and editing, hundreds of ready-to-run workflows, and support for thousands of custom nodes and models, including community-uploaded open-source models or user uploads like checkpoints and LoRAs that integrate instantly into workflows. Users can browse and launch workflows with one click, collaborate with team members in shared workspaces that keep private models, inputs, outputs, and settings centralized, and construct a private, production-ready library of workflows tailored to their pipeline.

Wan2.2 is a major upgrade to the Wan suite of open video foundation models, introducing a Mixture‑of‑Experts (MoE) architecture that splits the diffusion denoising process across high‑noise and low‑noise expert paths to dramatically increase model capacity without raising inference cost. It harnesses meticulously labeled aesthetic data, covering lighting, composition, contrast, and color tone, to enable precise, controllable cinematic‑style video generation. Trained on over 65 % more images and 83 % more videos than its predecessor, Wan2.2 delivers top performance in motion, semantic, and aesthetic generalization. The release includes a compact, high‑compression TI2V‑5B model built on an advanced VAE with a 16×16×4 compression ratio, capable of text‑to‑video and image‑to‑video synthesis at 720p/24 fps on consumer GPUs such as the RTX 4090. Prebuilt checkpoints for T2V‑A14B, I2V‑A14B, and TI2V‑5B stack enable seamless integration.

Happy Horse is an AI video generation and editing platform that helps users turn creative ideas into cinematic videos. The platform supports video creation from text, reference inputs, and first-frame prompts, giving creators flexible ways to bring visual concepts to life. Users can also edit videos by modifying details and refining generated results. Happy Horse features a creative community showcase with short films, featured videos, and AI cinema projects. The platform includes credits for generation, promotional offers, and tools for experimenting with imaginative video concepts. Happy Horse helps creators, artists, filmmakers, and storytellers capture ideas quickly and transform them into expressive AI-generated video content.

HappyHorse 1.1 is an upgraded AI video generation model designed to improve professional content creation across short dramas, ecommerce advertising, brand marketing, CG, and cinematic storytelling. The model enhances motion expressiveness, subject consistency, multi-reference fusion, instruction following, visual quality, and audio performance. HappyHorse 1.1 produces smoother actions, stronger kinetic tension, more natural pacing, and better temporal consistency in complex scenes. It also improves the preservation of product details, brand elements, character identity, storyboard references, and multi-panel inputs. The model delivers more realistic imagery, refined skin detail, stronger camera language, improved lip sync, richer sound design, and better audio-visual alignment. HappyHorse 1.1 helps creators, developers, and enterprise teams generate more controllable, coherent, and production-ready AI videos.