Image generation

Generate images with AUTOMATIC1111, ComfyUI workflows and LoRAs, or on-device Core ML Stable Diffusion in LM Mini.

Answer first

LM Mini can drive image models on your PC (A1111 / ComfyUI) or, on supported iPhones, run Core ML Stable Diffusion on-device. Personas can bind a preferred ComfyUI workflow.

Choose a backend

Settings → Image Generation

BackendNeedsNotes
AUTOMATIC1111A1111 WebUI API reachableClassic txt2img, HR fix
ComfyUIComfyUI server + API workflowFull graphs, LoRAs via placeholders
On-device (Core ML)iOS build with SD assetsPrivate; LoRA/VAE not mirrored yet

Master toggle: Image generation enabled. Optional review prompt before send and auto-generate on replies.

Home on Mac can proxy A1111 / ComfyUI on that Mac through Share with phone, same idea as chat.

AUTOMATIC1111

  1. Launch WebUI with the API enabled
  2. Paste the base URL into LM Mini
  3. Pick checkpoint, sampler, steps, CFG, size, optional HR / face restore
  4. Generate from the image button in chat

ComfyUI & LoRAs

  1. Select ComfyUI and enter the server URL
  2. Use the default workflow, paste API-format JSON, or pick a saved API workflow from the server
  3. Placeholders in string node inputs are filled at request time:

%PROMPT% %NEGATIVE% %SEED% %STEPS% %CFG% %WIDTH% %HEIGHT% %SAMPLER% %SCHEDULER% %CHECKPOINT% %LORA% %LORA_WEIGHT%

  1. Set LoRA name/weight in Image Generation settings when the graph expects %LORA%
Tip

Export workflows from ComfyUI in API format, not the UI-only graph JSON.

On-device Core ML (iOS)

Download a supported checkpoint from the on-device SD models screen, select it under Image Generation → On-device, then generate without a PC. Advanced LoRA/VAE paths that need PyTorch weights are not on-device yet. macOS UI for this path may still be hidden.

Personas

Art-oriented Personas can store a default ComfyUI workflow so character chats jump into the right graph.