CHIM Image-to-Text
Image-to-text is the vision side of CHIM. In normal use, this mainly means Soulgaze: CHIM looks at a screenshot, reads what is on screen, and turns that into useful context for your game.
How Soulgaze Works
When you use Soulgaze, CHIM takes a screenshot and sends it to your chosen image-reading service. It also passes along helpful context like who is visible and where you are, so the result is more useful than a plain screenshot description.
The Soulgaze hotkey has three gestures:
- Tap: Capture visual context without speech.
- Double-tap: Aim at an activated AI NPC to update their portrait.
- Hold: Ask the nearest activated NPC to describe the scene.
Finished images are saved into your Soulgaze gallery with scene information such as the location and capture time. CHIM can reuse those descriptions later so a place keeps a consistent visual identity.
Soulgaze Notes
Soulgaze works best when the screen clearly shows what you want CHIM to notice. If you turn on Soulgaze HD Mode, CHIM uses a higher-quality capture path for cleaner image reading, but it is heavier and VR users will usually want it off.
In the Soulgaze Gallery, use Lock as Location Description on the capture that best represents a place. Locked descriptions stay available as location context until you replace or unlock them. See Soulgaze Gallery for the gallery controls.
Recommended Image-to-Text Service
OpenRouter is the main recommended option. It is the easiest general-purpose choice if you want Soulgaze working without setting up your own local image service.
Other Supported Image-to-Text Services
OpenAI is direct OpenAI image reading. It is a good fit if you already use OpenAI for the rest of your setup.
Google OpenAI uses Google's image-reading models. It is a good fit if you prefer Google's model family.
Custom is for people running their own image-reading service or using a special provider that is not one of the built-in defaults.
llama.cpp is a local self-hosted option for people who want image reading on their own machine.
Ask An NPC To Describe The Scene
Use the Soulgaze controls in Prisma chat or the assigned hotkey to capture the scene or a character.
- Scene description: Ask an NPC to describe what they see. The spoken description uses their personality, speech style and voice.
- Portrait: Frame the character you want before taking the NPC photo.
- Capture choices: Choose the appropriate capture or upload option in the Soulgaze dropdown. Review the saved result in the gallery.