{% extends "base.html" %} {% block title %}Image generation · {{ profile.name }}{% endblock %} {% block content %}
Benchmarks an image-generation model's throughput (Lemonade's sd-cpp/thenoise recipes,
/v1/images/generations). Deliberately separate from the model/router leaderboard --
images/sec isn't comparable to LLM token throughput. This runs synchronously.
Couldn't reach this instance ({{ capabilities.error }}) -- engine and backend fall back to free text.
{% endif %}No image-generation results yet.
{% else %}| Timestamp | Model | Generation (ms) | Images/sec | Size | Steps | Valid | Notes |
|---|---|---|---|---|---|---|---|
| {{ r.timestamp }} | {{ r.model.name }} | {{ "%.1f"|format(r.metrics.generation_time_ms) }} | {{ "%.2f"|format(r.metrics.images_per_sec) }} | {{ r.metrics.image_size }} | {{ r.metrics.steps }} | {{ "valid" if r.validity.valid else "invalid" }} | {{ r.validity.notes or "" }} |