Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.lmsa.app/llms.txt

Use this file to discover all available pages before exploring further.

LMSA lets you generate images without leaving the chat interface. Type a slash command with your description and an image appears directly in your conversation thread. You can view it full-screen, save it, or keep chatting — the image stays in your chat history alongside your messages.

​
Generating an image

Type /image followed by your description in the chat input bar, then tap Send. 
/image a futuristic city at night, neon lights, cyberpunk style
LMSA sends your prompt to your connected provider’s image generation endpoint and the result appears inline in the chat within a few seconds.

​
Tips for better results

Include style cues like photorealistic, oil painting, watercolor, anime, or pencil sketch to steer the visual style of the output.
Prompts like wide-angle shot, close-up portrait, golden hour lighting, or dramatic shadows give the model more to work with and produce more intentional results.
Focus your prompt on what you want to appear rather than what you want to exclude. Short, vivid descriptions outperform long lists of exclusions.

​
Viewing and saving images

Tap any generated image in the chat to open it full-screen. From the full-screen view you can save the image to your device’s gallery.

​
Usage limits

Free users can generate a limited number of images. Once you reach the limit, LMSA prompts you to upgrade to Premium to continue.
Image generation requires your connected provider to support it. LM Studio and Ollama support image generation when a compatible model (such as a Stable Diffusion model) is loaded. OpenRouter also supports image generation with compatible models. If your current model does not support image generation, the /image command will return an error from the provider.