13 Commits

Author SHA1 Message Date
Aodhan Collins
0b8802deb5 Add Checkpoints Gallery with per-checkpoint generation settings
- New Checkpoint model (slug, name, checkpoint_path, data JSON, image_path)
- sync_checkpoints() loads metadata from data/checkpoints/*.json and falls
  back to template defaults for models without a JSON file
- _apply_checkpoint_settings() applies per-checkpoint steps, CFG, sampler,
  base positive/negative prompts, and VAE (with dynamic VAELoader node
  injection for non-integrated VAEs) to the ComfyUI workflow
- Bulk Create from Checkpoints: scans Illustrious/Noob model directories,
  reads matching HTML files, uses LLM to populate metadata, falls back to
  template defaults when no HTML is present
- Gallery index with batch cover generation and WebSocket progress bar
- Detail page showing Generation Settings and Base Prompts cards
- Checkpoints nav link added to layout
- New data/prompts/checkpoint_system.txt LLM system prompt
- Updated README with all current galleries and file structure
- Also includes accumulated action/scene JSON updates, new actions, and
  other template/generator improvements from prior sessions

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-26 21:25:23 +00:00
0d7d4d404f Merge pull request 'Added scene and actions browser.' (#5) from scenes-browser into master
Reviewed-on: #5
2026-02-22 23:45:22 +00:00
Aodhan Collins
615c400024 Added scene and actions browser. 2026-02-22 23:44:28 +00:00
bb65486995 Merge pull request 'Added style browser.' (#4) from style-browser into master
Reviewed-on: #4
2026-02-20 21:23:38 +00:00
Aodhan Collins
8487b177b4 Added style browser. 2026-02-20 21:22:53 +00:00
116941673e Merge pull request 'feat: implement Actions Gallery with character integration and triple LoRA chaining' (#3) from action-browser into master
Reviewed-on: #3
2026-02-19 20:07:17 +00:00
Aodhan Collins
467c90594c feat: implement Actions Gallery with character integration and triple LoRA chaining
- Added Actions gallery with CRUD and JSON sync
- Implemented Triple LoRA workflow (Character -> Outfit -> Action)
- Added character-integrated previews for Actions with style matching
- Implemented granular prompt selection and default persistence for Actions
- Added detailed development guide for extending gallery features
2026-02-19 20:06:57 +00:00
a4a21051a5 Merge pull request 'Add outfit gallery and AI-powered creation for characters and outfits' (#2) from clothing-gallery into master
Reviewed-on: #2
2026-02-19 18:36:02 +00:00
Aodhan Collins
c0e6cff7b7 Add outfit gallery and AI-powered creation for characters and outfits
- Add outfit gallery with CRUD operations (create, read, update, delete)
- Add AI-powered profile generation for both characters and outfits
- Add toggle to switch between AI generation and manual creation
- Auto-generate filenames from names with incrementing for duplicates
- Add 'full_body' and 'bottom' fields to wardrobe structure
- Update all character and outfit JSON files with new wardrobe fields
- Reorganize data into data/characters and data/clothing directories
- Update README with new features and JSON structure documentation
2026-02-19 18:34:46 +00:00
369c92e3ea Merge pull request 'Expanded generation options. Multiple outfits support.' (#1) from expanded-generation into master
Reviewed-on: #1
2026-02-19 00:41:30 +00:00
Aodhan Collins
5aede18ad5 Expanded generation options. Multiple outfits support. 2026-02-19 00:40:29 +00:00
Aodhan Collins
1e7f252cf9 Fixed broken generate buttons 2026-02-08 02:09:54 +00:00
Aodhan Collins
df82d4ec07 Initial implementation of Character Browser & Generator: Gallery, ComfyUI integration, progress tracking, and batch processing. 2026-02-08 01:54:18 +00:00