modelbeast/server
m3ultra 9c7164f77a comfyui_sd: fail fast when a checkpoint/LoRA isn't on the routed node
Checkpoints are no longer uniform across the fleet (M3 keeps only the
LoRA-compatible SD1.5 model; M1 holds the full SDXL archive). The gpu pool
routes by operator, not by checkpoint, so a job asking for bigLust could land
on a node without it. Query the node's own ComfyUI /object_info and exit with
the available list + where the rest lives, instead of a cryptic 400.
2026-07-17 01:44:17 +10:00
..
operators comfyui_sd: fail fast when a checkpoint/LoRA isn't on the routed node 2026-07-17 01:44:17 +10:00
__init__.py Phase 0 baseline: FastAPI+SQLite operator pipeline, React/three.js UI, ffprobe/ffmpeg_frames/blender_convert operators 2026-07-12 21:05:22 +10:00
auth.py Security hardening from adversarial review (5-agent workflow) 2026-07-13 12:25:13 +10:00
db.py Security hardening from adversarial review (5-agent workflow) 2026-07-13 12:25:13 +10:00
main.py Security hardening from adversarial review (5-agent workflow) 2026-07-13 12:25:13 +10:00
registry.py Phase 0 baseline: FastAPI+SQLite operator pipeline, React/three.js UI, ffprobe/ffmpeg_frames/blender_convert operators 2026-07-12 21:05:22 +10:00
remote.py runner: gpu lane becomes a node pool (local + remote workers) 2026-07-14 13:38:34 +10:00
runner.py pool cpu lane across nodes; hunyuan Studio-quality defaults 2026-07-16 10:59:44 +10:00
settings.py Security hardening from adversarial review (5-agent workflow) 2026-07-13 12:25:13 +10:00
store.py Security hardening from adversarial review (5-agent workflow) 2026-07-13 12:25:13 +10:00
sysinfo.py runner: gpu lane becomes a node pool (local + remote workers) 2026-07-14 13:38:34 +10:00