Image providers
What is painted
Character portraits at creation, inline scene art as the story moves, location pictures for new places, campaign covers, and world-pack art if you generate it. Battle maps, tokens, effects and the interface are painted on your device from shipped art and never need an image backend; without one, painted head-and-shoulders portraits for every race and class (masculine, feminine and neutral) stand in. At a table that plays in another language, the story text is rewritten into English inside the image job, since image models read English best.
The backends
| Backend | Needs | Where | Notes |
|---|---|---|---|
| OpenAI-compatible | A key | Apps: the Story AI OpenAI door lends its key. Server: Admin, Images, or OPENAI_IMAGE_API_KEY | No GPU. Model gpt-image-1 by default; fast and slow map to medium and high. A campaign key covers that campaign's scene art and maps; covers and library portraits use the server's own key. |
| ComfyUI | A GPU with 8 GB or more and an SDXL-class checkpoint | Server: Admin, Images, URL http://127.0.0.1:8188, checkpoint or Auto. Desktop app: the guided install, or the world's admin panel | Free and private. Any checkpoint, or Z-Image Turbo, whose files the server finds from ComfyUI's own lists; the setting supplies the style. 25 steps, CFG 6, 1024 or 1344 long side. |
| FLUX worker (MFLUX on a Mac, SDNQ elsewhere) | The ultra-fast-image-gen worker on :7869 | Server: Admin, Images | FLUX.2-klein at four steps, 1024 long side, 2048 for slow, up to two reference images. |
| The server's agent | Codex or Grok Build, after a test picture | Admin, Agent | Offered only once one real image has succeeded. |
In the apps
The OpenAI door on the Story AI screen sets the image backend to OpenAI on the same key, so pictures work the moment narration does. The Local AI on this machine door on Windows and Linux offers Install image generation (ComfyUI): ComfyUI with Stable Diffusion XL on your GPU, about 15 GB including Python packages, needing Python 3 and Git installed first. Anything else (a ComfyUI already on your network, the FLUX worker) is set in the world's admin panel, account menu, Admin, Images.
Per campaign
The Setup tab has pictures on or off, their shape (landscape, portrait, square) and fast or slow. On a self-hosted server it can also pick the backend per campaign. An old or interrupted request shows Image tool requested with a Generate button, and any picture can be uploaded by hand wherever the AI would paint one.
Cost and speed
- OpenAI: per image, at the model's price for the quality chosen. Pictures are the expensive part of a session; fast quality or landscape-only keeps it down, and off costs nothing.
- ComfyUI and the FLUX worker: free, and as fast as the GPU. On a shared GPU a render is queued behind the Dungeon Master's turn and behind narration.
Checking
The Setup tab reports the campaign's real image capability. Placeholders where a picture should be mean the backend is unreachable: check the URL (from Docker, host.docker.internal), that ComfyUI has a checkpoint loaded, or that the key has credit. The ComfyUI reachability probe in the admin panel is administrator-only on purpose.