BrowseCreate
Wiki/Images/Image Engines: Prism, Forge & Anime

🧩Image Engines: Prism, Forge & Anime

The three image models and what each one is best at.

AI Peeps has three image engines. You can pick one per image, and a Peep's appearance sets a default.

🔥 Forge — the flexible all-rounder

Forge is an image edit model: it can create images from scratch and edit existing ones, in any style — realistic, anime, painting, surreal, whatever. It understands natural language, so you just describe what you want.

Example prompt:

A woman in a red sundress sitting on a sunlit balcony, sipping coffee, warm morning light
  • Works with or without a Peep.
  • The only engine that edits and combines images — it can blend up to 3 on-site images (Peep or generated) into one. See Editing & Combining.

📷 Prism — realistic

Prism specializes in photorealistic images and uses Booru tags (keywords). Its look is more detailed, more saturated and a touch more stylized, and it can generate the widest range of NSFW content.

Example prompt:

1girl, red sundress, balcony, morning light, sitting, coffee, looking at viewer

You can also weight tags — see the Prompting Guide.

🧚 Anime — illustrated

Anime renders illustrated / anime art, also via Booru tags, with 14 sub-styles: Default, Vintage, Drawbook, Sketch, Retro, Detailed, Detailed Monochrome, Watercolors, Rainbow, Stilized, Pixel Art, Cute, Bimbo, and More Realistic.

Forge or Prism for realism?

They have genuinely different artistic styles, so it comes down to taste:

  • Prism — more detailed, more saturated, a touch more stylized, and the most varied NSFW.
  • Forge — excellent at SFW and easier to prompt; it does plenty of NSFW too, just not as much as Prism.
💡 Tip
Start with Forge — it's easier to prompt and more consistent. But don't forget Prism: it can generate absolute beauties.
📌 Note
When you create a new Peep, the very first image can only be Prism (realistic) or Anime — not Forge. After that, you can use any engine.