- Add sampler/scheduler/steps/vae to MODEL_FAMILY_DEFAULTS for all families
- Add zimage family detection for ZImageTurbo models
- Flux and zimage families use ae.safetensors VAE
- SD 1.5 families use checkpoint built-in VAE
- SDXL families use sdxl_vae.safetensors
- API auto-applies family defaults when request uses default values
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Log prompt, model, size, steps on generate request
- Log completion with prompt_id and image count
- Log warnings/errors on failures
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use sdxl_vae.safetensors by default instead of checkpoint VAE
- Add vae parameter to generate_image and API endpoint
- Better quality for modern SDXL-based models
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace polling with WebSocket connection for real-time progress
- Show step-by-step progress during sampling (Step 1/20, etc.)
- Display progress bar with actual completion percentage
- Fall back to polling if WebSocket connection fails
- Import websocket-client for sync WebSocket support
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The /comfy/{path} proxy route was generating duplicate operationIds
for each HTTP method, causing OpenAPI validation to fail.
Exclude all ComfyUI proxy/auth routes from schema - they're not meant
to be used by API clients.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add FastAPI routes for ComfyUI programmatic API:
Query endpoints:
- GET /api/comfyui/status - System stats (GPU, RAM, etc.)
- GET /api/comfyui/queue - Queue status (running/pending)
- DELETE /api/comfyui/queue - Clear the queue
- GET /api/comfyui/models - List available models
- GET /api/comfyui/history - List generation history
- GET /api/comfyui/history/{prompt_id} - Get specific result
Generation endpoints:
- POST /api/comfyui/generate - Text-to-image with full params
- POST /api/comfyui/workflow - Queue arbitrary API-format workflow
All endpoints protected with API key auth (X-API-Key header).
Pydantic models for request/response validation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add ComfyUI CLI subcommand group with:
- `tsr comfy status` - System stats (GPU, RAM, PyTorch, queue)
- `tsr comfy queue` - Show queue status (running/pending)
- `tsr comfy queue --clear` - Clear the queue
- `tsr comfy models` - List available checkpoints, LoRAs, VAE, etc.
- `tsr comfy history [ID]` - View generation history
- `tsr comfy generate` - Text-to-image with full parameter control
- prompt, negative, model, width, height, steps, cfg, seed
- sampler, scheduler selection
- optional --output to save locally
- `tsr comfy run workflow.json` - Run arbitrary API-format workflows
All commands support --json output and --url for custom server.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
aladac
github-actions[bot]
Adam Ladachowski
Adam Ladachowski