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>
This commit is contained in:
Aodhan Collins
2026-02-26 21:25:23 +00:00
parent 0d7d4d404f
commit 0b8802deb5
334 changed files with 9437 additions and 3772 deletions

View File

@@ -2,31 +2,31 @@
"action_id": "srjxia",
"action_name": "Srjxia",
"action": {
"full_body": "standing, leaning on object, leaning on sword, confident pose, solo",
"head": "looking at viewer, arrogant expression, slight head tilt",
"eyes": "purple eyes, narrow gaze",
"arms": "one hand on hip, one hand holding sword handle",
"hands": "resting on sword hilt, hand on hip",
"torso": "straight posture, slight twist",
"pelvis": "weight shifted to one leg",
"legs": "crossed legs or standing relaxedly",
"feet": "standing on ground",
"additional": "giant sword, claymore, weapon, embers, magma, fire particles"
},
"participants": {
"solo_focus": "true",
"orientation": "MF"
"full_body": "minigirl sitting inside a glass jar",
"head": "looking at viewer",
"eyes": "open eyes",
"arms": "arms close to body, cramped space",
"hands": "hands on legs or pressing against glass",
"torso": "leaning forward or upright",
"pelvis": "sitting on bottom of jar",
"legs": "knees directly up, knees to chest",
"feet": "bare feet or shoeless",
"additional": "transparent glass, reflection, confined space"
},
"lora": {
"lora_name": "Illustrious/Poses/srjxia.safetensors",
"lora_weight": 1.0,
"lora_triggers": "srjxia"
"lora_triggers": "GirlInGlassJar"
},
"tags": [
"arknights",
"character focus",
"demon girl",
"weapon focus",
"anime style"
"minigirl",
"jar",
"glass",
"in_container",
"sitting",
"knees_to_chest",
"stuck",
"cramped",
"trapped"
]
}