Jedrzej Kosinski aeb3c77ae9 Cube3D: route VAE decode through managed comfy.sd.VAE.decode ... Stop fighting ComfyUI's model management. VAEDecodeCube was manually calling load_models_gpu + .to(vae.device) and the VAE forced disable_offload=True because it bypassed the managed decode path. Now CubeShapeVAE.decode(samples) is the entry point that comfy.sd.VAE.decode calls, so loading/device/dtype are handled automatically (like Hunyuan3Dv2): - removed disable_offload=True (let the offload system manage weights) - removed manual load_models_gpu + .to(device) from the node - process_output set to identity (default clamps [0,1] in-place and would destroy the occupancy isosurface) - decode() pre-inverts VAE.decode's trailing movedim(1,-1) so the node receives grid logits unchanged (parity preserved) - memory_used_decode sized by num_tokens (shape[-1]) for the new latent layout Amp-Thread-ID: https://ampcode.com/threads/T-019ec361-addb-70d8-a74b-438ce8a1e096 Co-authored-by: Amp <amp@ampcode.com>		2026-06-14 23:28:22 -07:00
..
gpt.py	Add native Roblox Cube3D text-to-3D support	2026-06-14 20:21:37 -07:00
vae.py	Cube3D: route VAE decode through managed comfy.sd.VAE.decode	2026-06-14 23:28:22 -07:00