aodhan/character-browser
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: implement Actions Gallery with character integration and triple LoRA chaining

Browse Source 
- 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
This commit is contained in:
Aodhan Collins
2026-02-19 20:06:57 +00:00
parent a4a21051a5
commit 467c90594c
11 changed files with 1350 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
templates/actions/create.html Normal file
View File

@@ -0,0 +1,74 @@
{% extends "layout.html" %}
{% block content %}
<div class="container">
<div class="row justify-content-center">
<div class="col-md-8">
<div class="card">
<div class="card-header bg-success text-white">Create New Action</div>
<div class="card-body">
<form action="{{ url_for('create_action') }}" method="post">
<div class="mb-3">
<label for="name" class="form-label">Action Name</label>
<input type="text" class="form-control" id="name" name="name" placeholder="e.g. Belly Dancing" required>
</div>
<div class="mb-3">
<label for="filename" class="form-label">Filename (Slug) <small class="text-muted">- optional, auto-generated if empty</small></label>
<input type="text" class="form-control" id="filename" name="filename" placeholder="e.g. belly_dancing">
<div class="form-text">Used for the JSON file and URL. No spaces or special characters. Auto-generated from name if left empty.</div>
</div>
<div class="mb-3 form-check form-switch">
<input class="form-check-input" type="checkbox" id="use_llm" name="use_llm" checked>
<label class="form-check-label" for="use_llm">Use AI to generate profile from description</label>
</div>
<div class="mb-3" id="prompt-group">
<label for="prompt" class="form-label">Description / Concept</label>
<textarea class="form-control" id="prompt" name="prompt" rows="5" placeholder="Describe the action, pose, or movement. The AI will generate the full action profile based on this."></textarea>
<div class="form-text">Required when AI generation is enabled.</div>
</div>
<div class="alert alert-info" id="ai-info">
<i class="bi bi-info-circle"></i> The AI will generate a complete action profile with pose details and tags based on your description.
</div>
<div class="alert alert-secondary d-none" id="manual-info">
<i class="bi bi-info-circle"></i> A blank action profile will be created. You can edit it afterwards to add details.
</div>
<div class="d-grid">
<button type="submit" class="btn btn-success btn-lg" id="submit-btn">Create & Generate</button>
</div>
</form>
</div>
</div>
</div>
</div>
</div>
<script>
document.getElementById('use_llm').addEventListener('change', function() {
const promptGroup = document.getElementById('prompt-group');
const aiInfo = document.getElementById('ai-info');
const manualInfo = document.getElementById('manual-info');
const submitBtn = document.getElementById('submit-btn');
const promptInput = document.getElementById('prompt');
if (this.checked) {
promptGroup.classList.remove('d-none');
aiInfo.classList.remove('d-none');
manualInfo.classList.add('d-none');
submitBtn.textContent = 'Create & Generate';
promptInput.required = true;
} else {
promptGroup.classList.add('d-none');
aiInfo.classList.add('d-none');
manualInfo.classList.remove('d-none');
submitBtn.textContent = 'Create Action';
promptInput.required = false;
}
});
</script>
{% endblock %}