Skip to content

Image Gen · Civitai

Civitai

Community hub for open image models — discover, share, and generate.

FREEMIUMOpen coreCloudWebAPI

The largest community platform for open generative-image models, hosting thousands of Stable Diffusion and Flux checkpoints, LoRAs, and embeddings. Creators upload models with sample galleries, and on-site generation lets you run them in the browser. Every shared image is paired with the model, prompt, and settings used to create it.

Where it runs

  • Web
  • API

Tags

  • #models
  • #stable-diffusion
  • #lora
  • #community
Open CivitaiGitHub

Related in Image Gen

  • View Midjourney details
    ImagePAID

    Midjourney

    Midjourney

    The brand-name image generator. Discord-native, web app available.

    Hosted image generation that defined the category. Strong aesthetic defaults, style references, and rich prompt-control vocabulary. Used by designers, illustrators, and prompt artists worldwide.

    AI insight: Ran Discord-only for years before shipping a web app — its opinionated house aesthetic is the trade-off for less fine control.

    • image-gen
    • design
    • illustration
    • style-reference
    Open
  • View Adobe Firefly details
    ImageFREEMIUM

    Adobe Firefly

    Adobe

    Commercially-safe generative AI for images, video, and design.

    Adobe's generative AI for creators — text-to-image, generative fill, and increasingly video, available as a standalone web app, mobile apps, and inside Creative Cloud tools like Photoshop. Built around Adobe's own Firefly models trained on licensed and public-domain content, with select third-party models now integrated. A free tier ships monthly credits; paid plans add more credits and IP indemnification.

    AI insight: Trained only on licensed and public-domain content, so paid-tier generations carry Adobe's IP indemnification — rare among image models.

    • image-gen
    • video
    • commercially-safe
    • design
    Open
  • View ComfyUI details
    ImageFREEMIUMOpen core

    ComfyUI

    Comfy Org

    Node-based visual AI — wire up image, video, and audio diffusion pipelines.

    An open-source, node-graph interface for diffusion models — build precise, reproducible image/video/audio pipelines on an infinite canvas where every model and parameter is visible. Runs locally on your own GPU or as a desktop app, with thousands of community nodes.

    AI insight: Exposes the whole diffusion pipeline as an explicit node graph, so a workflow is reproducible and shareable as a single JSON file.

    • image-gen
    • video-gen
    • node-based
    • open-source
    Open
  • View FLUX details
    ImageFREEMIUM

    FLUX

    Black Forest Labs

    Black Forest Labs' open image models — sharp prompt adherence.

    The FLUX family from Black Forest Labs — open and pro image models known for crisp detail and strong prompt following. Usable via the BFL playground, API, and across the ecosystem.

    AI insight: From the team that created Stable Diffusion — it ships open weights alongside a hosted pro tier for its strongest models.

    • image-gen
    • open-weights
    • api
    • flux
    Open
  • View Leonardo AI details
    ImageFREEMIUM

    Leonardo AI

    Leonardo AI

    Image generation with fine-tuned models, control, and game-asset focus.

    Image platform with custom fine-tuned models, ControlNet-style guidance, real-time canvas, and upscaling. Popular with game studios and concept artists for consistent asset pipelines.

    AI insight: Built for consistent game-asset pipelines via custom fine-tuned models — and now owned by Canva.

    • image-gen
    • game-assets
    • control
    • upscaling
    Open
  • View Recraft details
    ImageFREEMIUM

    Recraft

    Recraft

    Design-grade image + vector generation with brand consistency.

    Image generator aimed at designers — raster and true vector (SVG) output, brand style sets, mockups, and precise control. Strong when assets need to ship into real design work.

    AI insight: Rare among image generators in outputting true editable SVG vectors — built to drop assets straight into real design work.

    • image-gen
    • vector
    • design
    • brand
    Open
  • View Ideogram details
    ImageFREEMIUM

    Ideogram

    Ideogram

    Image gen with the best text-in-image quality.

    Hosted image generator with industry-leading typography rendering — actually readable text inside images. Strong for logos, posters, social cards, and any composition where letterforms matter.

    AI insight: The one to reach for when the image needs legible text — readable typography inside generations is its whole differentiator.

    • image-gen
    • typography
    • posters
    • logos
    Open
  • View Krea details
    ImageFREEMIUM

    Krea

    Krea AI

    Design-loop image surface. Generate, edit, upscale, iterate.

    Multi-model creative canvas — image generation, real-time edits, upscaling, and style transfer chained together. Strong for fast iteration on a single image rather than rolling fresh prompts.

    AI insight: Fronts several engines (Flux, Imagen, Sora) on one real-time canvas, built to refine a single image rather than re-roll prompts.

    • image-gen
    • editing
    • upscaling
    • design
    Open
  • View Magnific details
    ImagePAID

    Magnific

    Magnific AI

    AI upscaling + relighting that goes beyond pixel-doubling.

    Upscales images while reimagining detail — adds plausible texture, lighting, and structure rather than just sharpening. Broke through with the 'AI photography' workflow for product shots and concept art.

    AI insight: Doesn't just sharpen — it invents plausible new detail on upscale, the magic for concept art and the caveat for real photos.

    • upscaling
    • enhancement
    • relighting
    • photography
    Open
Open Civitai