Model selection:
- Add sdxl_offload tier (eff_vram ≥ 4.0 GB) for GTX 1060 6GB and Quadro
6GB cards that were falling through to SD 2.1 despite SDXL fitting with
model_cpu_offload. Cards with 5.3 GB effective VRAM now get SDXL quality.
- Update _tier_label(), _caps(), _build_warnings() for new tier.
Frontend GPU display:
- api.js: add getGpuStatus() fetching /api/gpu/status
- capabilities.js: add getGpuStatus() export with own LRU cache;
refreshCapabilities() now also resets GPU status cache
- provider-badge.js: when AI_PROVIDER=local_gpu show green badge with
GPU name, tier, VRAM, CC, feature flags, and capabilities in tooltip.
Strip "NVIDIA GeForce" prefix so "GTX 1060 6GB" fits in badge.
- ai_provider_settings.js: add local_gpu to all provider dropdowns;
show GPU info panel (device, VRAM, CC, features, tier, model table per
operation) in the settings dialog when a GPU is detected.
https://claude.ai/code/session_01WVDg7amsy1TTtxvpku7bcM
Backend:
- sam_service.py: auto-downloads SAM ViT-B (~375 MB) on first use with
progress tracking; loads model to CUDA/MPS/CPU; predict_points() takes
multi-point prompts (include/exclude labels) and returns best mask
- POST /api/segment/point: SAM point-prompt endpoint; returns mask PNG
- GET /api/segment/install-status: poll download progress
- POST /api/segment/install: explicit trigger (also auto on first click)
- main.py: pre-download SAM on startup alongside NCNN
Frontend (ai_edit.js):
- Click mode (default): click object → SAM generates mask instantly
Alt+click → subtract (deselect over-selected area)
Multiple clicks accumulate for multi-object or refinement
- Brush + / Brush − modes: paint to add or erase from SAM mask by hand
- If SAM model is still downloading on first click: inline progress bar,
user retries the click when done
- Unified action bar: Erase | Replace (inline prompt) | Upscale | Expand | Clear
- All modes share the same mask canvas; SAM and brush are fully composited
https://claude.ai/code/session_01B58MaJCU1R6KwBDJCp8AfN
- Add _vulkan_available(): checks /dev/dri/renderD* on Linux, assumes
true on macOS/Windows; set REALESRGAN_NCNN=force to override
- Add _test_ncnn_binary(): test-runs the binary after install and checks
stderr for "no vulkan" — marks skipped if Vulkan init fails at runtime
- ensure_ncnn_installed() now returns early with state=skipped when no
Vulkan detected, avoiding a wasted ~30MB download on CPU-only servers
- Recommend PyTorch CPU when available on headless (AI quality, slow but
works); Lanczos as final fallback
- Frontend: handle state=skipped immediately (no polling needed), show
brief informational toast; show "Headless server" note in dialog
https://claude.ai/code/session_01B58MaJCU1R6KwBDJCp8AfN
- upscale.py: add InstallStatus dataclass + ensure_ncnn_installed() async
function that downloads and extracts the NCNN binary for the current
platform (Linux/macOS/Windows), tracks progress (0-100%), and busts the
caps cache when done
- main.py: trigger ensure_ncnn_installed() as a background task on app
startup when no AI upscaler is detected
- print_tools.py: /upscale/available triggers install task when no AI
upscaler found; new GET /upscale/install-status endpoint for polling
- upscale.js: if no AI upscaler on open, poll install-status showing a
progress bar notification, then refresh caps and proceed when done
https://claude.ai/code/session_01B58MaJCU1R6KwBDJCp8AfN
Detection priority (probed once, cached):
1. Real-ESRGAN PyTorch + CUDA GPU → fastest, best quality
2. Real-ESRGAN PyTorch + Apple MPS → fast on Apple Silicon
3. Real-ESRGAN NCNN Vulkan binary → fast on any GPU via Vulkan (no CUDA needed)
4. Real-ESRGAN PyTorch CPU → works, slow (warned in UI)
5. Lanczos → always available, instant fallback
Backend:
- services/upscale.py: full capability probe (probe_upscale_capabilities),
implementations for PyTorch (CUDA/MPS/CPU auto-device) and NCNN binary,
upscale_sync() resolves method with fallback chain,
async upscale_image() runs in thread pool
- print_tools.py: /api/print/upscale uses new service; method="auto" by default;
GET /api/print/upscale/available returns full capability map with device info
and recommended_label; POST /api/print/upscale/refresh-caps busts cache
without restart (useful after installing NCNN binary into container)
Frontend:
- upscale.js: fetches capability map on first open; builds method selector showing
only available options; labels recommended method with ★; shows device info
(CUDA/MPS/CPU/NCNN) in dialog; maps display label back to method key on submit;
shows actual method used in success toast and undo history entry
Scripts:
- scripts/download_realesrgan.py: downloads NCNN Vulkan binary for current platform
(Linux/macOS/Windows) to /app/data/models/realesrgan/; makes executable;
run inside container or locally
https://claude.ai/code/session_01B58MaJCU1R6KwBDJCp8AfN
Each operation (inpaint, txt2img, img2img, outpaint) can now use a different
provider. Resolution order: per-op override → global AI_PROVIDER default.
Example: txt2img→openai, inpaint→invokeai, everything else→invokeai default.
Backend:
- config.py: add AI_PROVIDER_INPAINT / TXT2IMG / IMG2IMG / OUTPAINT settings
- remote_provider.py: get_remote_provider(operation) resolves override then default;
_build_provider() extracted as shared factory; _OP_FIELD maps op→setting name
- ai_tools.py: each endpoint passes its operation to _require_remote();
GET /api/config runs per-op health checks concurrently, returns operations map
and overrides; POST /api/config accepts and applies per-op override fields
Frontend:
- ai_provider_settings.js: four new selects (inpaint/txt2img/img2img/outpaint);
persists to localStorage and sends per-op fields to POST /api/config
- provider-badge.js: shows override summary (e.g. "invokeai · txt2img→openai")
and per-op health in tooltip
- .env.example: document per-op override env vars with examples
https://claude.ai/code/session_01B58MaJCU1R6KwBDJCp8AfN
- Fix My Library: Add CSS styling for library browser, items now visible
- Integrate My Library into Shapes tool with tabbed interface
- Improve AI Inpaint: Add transform mode for scaling/sizing selections
- Add helpful guidance explaining inpaint vs transform modes
- Add U2net as alternative background removal (avoids rembg issues)
- Create U2net model definition and download script
- Improve Caddyfile with multiple options and troubleshooting guide
Note: Brush Select (AI Paint) tool was already implemented and working.
https://claude.ai/code/session_01CLedz6CanT9t46KBvng3vz
Backend:
- Add /tools router with background removal, smart select, color select
- Add rembg dependency for AI background removal
- Add layer management API (list, flatten)
- Fix transparency preservation in blend_patch (veil collapse fix)
- Preserve alpha channel when reverting/resetting images
Frontend:
- Add AdvancedTools panel with background removal, smart select, color select
- Add Layers panel with drag-to-reorder, visibility toggle, flatten
- Add toolsApi for new backend endpoints
- Make right panel scrollable for additional controls
This adds "Photoshop light" capabilities:
- Remove background and create layer
- Smart object selection (click to select)
- Color selection with tolerance
- Layer system with compositing
Implemented complete text-to-image functionality across all AI providers:
Backend additions:
- Added text_to_image() method to AIProvider abstract class
- Implemented for all providers:
* OpenAI: DALL-E generations API
* Stability AI: SDXL text-to-image with negative prompts
* Replicate: SDXL with full parameter control
* Mock: Placeholder image generation for testing
New API endpoints (/generate):
- POST /generate/text-to-image
* Generate image from prompt
* Optional: create new project automatically
* Configurable width/height (256-2048px)
* Negative prompt support
* Provider and model selection
- POST /generate/layer/text-to-image
* Generate image as layer in existing project
* Smaller dimensions for layer composition
* Position control (x, y coordinates)
* Saves to project layers directory
Features:
- Full provider support (OpenAI, Stability, Replicate, Mock)
- Negative prompts for better control
- Auto-project creation option
- Layer-based generation for compositing
- Dimension validation (256-2048px range)
- Model selection per request
Use cases:
- Create new images from scratch
- Generate elements to add as layers
- Quick ideation and iteration
- Base image creation for further editing
Next: Advanced canvas UI with layers and real-time preview
Major additions:
1. Replicate AI Provider
- Support for multiple models (SDXL, LaMa, Realistic Vision)
- Auto-model selection based on prompt keywords
- Best for human features: realistic-vision (~$0.020/image)
- Best for removal: lama (~$0.002/image)
- Best general purpose: sdxl-inpaint (~$0.025/image)
- Smart keyword detection for automatic model selection
2. Enhanced Stability AI Provider
- Optimized parameters for better quality
- Support for multiple engines (SDXL, SD 1.5, SD 2.1)
- Increased steps and CFG scale for improved results
3. Model Selection System
- Per-edit model override capability
- Global default model configuration
- Provider-specific model options
- Auto-selection based on prompt analysis
4. Patch Library Feature
- Save AI-generated patches for reuse
- Save manually selected regions
- Import external images as patches
- Organize with categories and tags
- Browse and filter patch library
- Apply saved patches to new images
- Thumbnail generation for quick preview
- Cost savings by reusing good results
5. Comprehensive Documentation
- MODEL_SELECTION_GUIDE.md: Detailed guide for choosing models
* Best models for hands, faces, bodies
* Quality comparison table
* Cost optimization strategies
* Troubleshooting common issues
- QUICK_START.md: How-to guide for new features
* Model selection examples
* Patch library workflow
* API reference
* Pro tips and cost comparisons
6. Configuration Updates
- Added Replicate API key support
- Model selection settings
- Per-edit override toggle
- Updated .env.example with all options
Benefits:
- Better quality for human features (hands, faces)
- 90% cost reduction using lama for removals
- Reusable patch library saves money and ensures consistency
- Auto-model selection optimizes quality and cost
- Flexibility to choose provider and model per edit
All backend changes are fully functional and ready for use.
Frontend UI for patch library pending.
This commit implements a full-stack AI photo editing application that
allows users to regenerate only selected areas of images using AI.
Features implemented:
- Frontend (React + Fabric.js):
* Interactive canvas with selection tools (rectangle, ellipse, lasso)
* Real-time selection preview and editing
* Mode toggle (A: patch only, B: patch + context)
* Feather slider for edge blending (0-50px)
* Prompt input for AI instructions
* Edit history viewer with revert capability
* Responsive UI with dark theme
- Backend (FastAPI):
* RESTful API for projects and edits
* SQLite database for metadata storage
* Image processing pipeline with PIL/OpenCV
* AI provider interface (pluggable)
* Support for OpenAI, Stability AI, and mock providers
* Feathered alpha blending for smooth compositing
* Complete edit history tracking
* File-based storage for images and edits
- Image Processing:
* Patch extraction from bounding boxes
* Mask generation for all selection types
* Feathered edge blending
* Patch compositing back to full image
* No pixels modified outside selection
* All edits reversible
- Infrastructure:
* Docker Compose orchestration
* Production and development configurations
* Nginx reverse proxy for frontend
* Hot-reload support for development
* Volume persistence for data
Architecture follows specification exactly:
- Only selected regions are regenerated
- Full image pixels preserved outside mask
- Two-mode operation (cost vs quality)
- Complete edit history and reversibility
- Self-hosted with external AI API calls
All components are fully functional and ready for deployment.
Claude