20 Commits
Author SHA1 Message Date
PozzettiAndrea 3cc4d96d65 updoot 2026-04-16 01:14:58 +02:00
PozzettiAndrea 127db2968e path in workflow 2026-02-21 18:50:13 +01:00
PozzettiAndrea b768bd9836 att 2026-02-21 16:18:12 +01:00
PozzettiAndrea 6ee188192f workflow update 2026-02-21 13:32:35 +01:00
PozzettiAndrea 8f1be7335a add memory dropdown (cache_gpu, cpu_offload, delete) to LoadSAM3DBodyModel
Adds model memory management with three strategies: keep on GPU, offload
to CPU RAM, or delete after inference. Updates all workflow JSONs.
2026-02-15 18:12:52 +01:00
PozzettiAndrea 4ff3fbe409 remove unused server routes that caused CUDA crash on CPU runners
The server.py endpoints (/sam3d/save_glb, /sam3d/export_posed_fbx) were
never called by the frontend. Importing PromptServer at module level
triggered model_management → torch.cuda.current_device() → access
violation on CPU-only machines during instantiation tests.
2026-02-15 16:36:20 +01:00
PozzettiAndrea 5acc182dd3 use flash attention 2026-02-15 15:58:45 +01:00
PozzettiAndrea 6461ec55e7 updated reqs 2026-02-11 22:35:43 +01:00
Andrea Pozzetti 0f6a211365 updated workflow 2026-02-11 22:14:43 +01:00
Andrea Pozzetti 8ccc865c7f new workflows 2026-02-11 22:12:43 +01:00
Andrea Pozzetti 2f401a145b updated install.py 2026-02-11 22:10:43 +01:00
Andrea Pozzetti c4ee3fad0e depth correction fix 2026-02-11 21:59:43 +01:00
Andrea Pozzetti 28c8467de6 added multiple people support 2026-02-11 21:43:43 +01:00
Andrea Pozzetti 7ac035aef1 depth correction 2025-12-28 19:42:19 +01:00
Andrea Pozzetti ac2fc601c2 partial progress 2025-12-28 15:35:55 +01:00
Andrea Pozzetti 0ddeefb3e8 started adding multi people 2025-12-01 01:04:44 +01:00
Andrea Pozzetti abcd5710df added loaders for fbx 2025-11-23 05:59:38 +01:00
Andrea Pozzetti 36cf8db318 added rigging 2025-11-23 05:58:38 +01:00
Andrea Pozzetti 84a000b355 first draft 2025-11-23 05:43:38 +01:00
Andrea Pozzetti 09135b8072 First draft 2025-11-23 05:42:38 +01:00