FLUX-1 Krea AI Image Generator
FLUX.1 Krea dev is a free online AI image generator based on BlackForestLabs' next-generation open-weights model, FLUX.1 Krea [dev]. It creates high-resolution, multi-style images from text prompts.
Ver2.0.0-beta.1
7982 tools indexed with fast category, pricing, and feature filters.
FLUX.1 Krea dev is a free online AI image generator based on BlackForestLabs' next-generation open-weights model, FLUX.1 Krea [dev]. It creates high-resolution, multi-style images from text prompts.
FLUX AI Image Generator is a free online tool based on Black Forest Labs' FLUX.1 [dev] model, providing high-quality text-to-image generation services without requiring login.
SDXL Turbo is a text-to-image generation tool leveraging Adversarial Diffusion Distillation (ADD) technology for single-step real-time image synthesis. Core features include rapid 512x512 image generation from text prompts, enhanced text rendering via CLIP/T5 encoders, and multimodal diffusion transformer architecture. Key characteristics: revolutionary ADD enables 207ms generation (A100 GPU), GAN ensures artifact-free clarity, and computational efficiency is significantly improved. Target users
Main features: AnimateDiff is an AI video generation tool supporting text-to-video and image-to-video conversion, transforming text descriptions or static images into animated videos. Core features include: text/image input animation, looping video creation, video editing (via ControlNet), personalized animation (with DreamBooth/LoRA), and creative workflow integration. Target users: artists, animators, game developers, content creators, educators, social media users. Key advantages: plug-and-pl
DeepFaceLab is a tool that utilizes deep learning recognition to exchange faces in images and videos. This technology can produce very realistic and natural face changing videos in specific situations. DeepFaceLab is one of the easiest, most convenient, and fastest to install software among many others
DeepFloyd IF is a modular composed of a frozen text encoder and three cascaded pixel diffusion modules: a base model that generates 64x64 px image based on text prompt and two super-resolution models, each designed to generate images of increasing resolution: 256x256 px and 1024x1024 px