Pictor · Image
AI image tools
AI image tools in this graph: 23, including Midjourney, Stable Diffusion WebUI, ComfyUI, Segment Anything, CLIP and FLUX.
Generate, edit and upscale pictures.
Capabilities in this galaxy
Products14
- Midjourney2022The benchmark for stylish, painterly image generation.Paid
- Stable Diffusion WebUI2022A self-hosted web interface for generating and editing images with Stable Diffusion models.Open source, free · Runs offline
- ComfyUI2023A node-based editor for building image and video pipelines on your own machine.Open source, free · Runs offline
- Adobe Firefly2023Adobe's commercially safe generator, built into Photoshop.Free plan + paid upgrades
- Ideogram2023An image generator that gets text right: posters, logos and signs.Free plan + paid upgrades
- Krea2022Real-time generation, upscaling and a hub for many image and video models.Free plan + paid upgrades
- Fooocus2023A local image generator on Stable Diffusion XL that keeps prompting as simple as Midjourney.Open source, free · Runs offline
- Invoke2022A creative app with a canvas and node workflows for Stable Diffusion and FLUX models.Open source, free · Runs offline
- Kohya's GUI2022A desktop GUI for training LoRA and fine-tuning Stable Diffusion, SDXL and FLUX models.Open source, free · Runs offline
- Civitai2022A community hub for sharing image models, LoRAs and generations.Free plan + paid upgrades
- Leonardo.Ai2022An image and video studio with fine control, popular for game and product art.Free plan + paid upgrades
- LiblibAI 哩布哩布2023One of China's largest communities for image models and workflows.Free plan + paid upgrades
- Magnific2023An upscaler that invents believable detail as it enlarges images.Paid
- Recraft2023Generates vector illustrations, icons and brand-consistent graphics.Free plan + paid upgrades
Frameworks1
Models8
- Segment Anything2023Meta's promptable segmentation models that cut out any object in images or video.Open source, free · Runs offline
- CLIP2021OpenAI's model that learns a shared embedding of images and text from captioned web images.Open source, free · Runs offline
- FLUX2024Photoreal image models from the original Stable Diffusion team, some with open weights.Open source, free · Runs offline
- StyleGAN2018NVIDIA's style-based GAN, known for photorealistic generated faces.Open source, free · Runs offline
- DALL·E2021OpenAI's family of text-to-image models.
- Nano Banana2025Google's Gemini-based image generation and editing model, known for consistent multi-turn edits.
- Stable Diffusion2022The open image model that launched a thousand community fine-tunes.Open source, free · Runs offline
- Imagen2022Google's family of text-to-image diffusion models.
Organizations11
- Midjourney2021An independent research lab that makes the Midjourney image generator.
- Stability AI2019A London AI company known for releasing the Stable Diffusion image models.
- Black Forest Labs2024A German image-model lab founded by original Stable Diffusion researchers; it makes FLUX.
- Civitai2022Company that runs Civitai, a community hub for sharing open image-generation models.
- Comfy Org2024Company formed by ComfyUI's core developers to maintain the open-source node-based generation tool.
- Ideogram2022Startup founded by former Google Brain researchers that makes the Ideogram image generator.
- Krea2022San Francisco startup that builds Krea, a real-time creative suite for image and video models.
- Leonardo.Ai2022Sydney-founded maker of the Leonardo.Ai image and video studio, acquired by Canva in 2024.
- LiblibAI 哩布哩布2023Chinese company behind the LiblibAI model community and the Lovart design agent.
- Magnific2010Málaga company, formerly Freepik, that runs the Magnific AI creative platform and upscaler.
- Recraft2022Startup that builds Recraft, an AI tool and model family for vector and brand graphics.
People1
Last updated 2026-09-24