40 Commits

Author	SHA1	Message	Date
Jukka Seppänen	c8c351b456	Merge pull request #44 from AustinMroz/main ... Support for compiling on AMD systems	2025-02-06 08:54:19 +02:00
kijai	89536cbd42	Update vae.py	2025-02-05 17:55:03 +02:00
kijai	44b9d0d676	Update vae.py	2025-02-05 17:18:27 +02:00
kijai	a148a02247	Add ODC ... https://github.com/KAIST-Visual-AI-Group/ODC/	2025-02-05 14:44:26 +02:00
kijai	87e2a4341f	add plain output mode for the mesh gen	2025-02-05 13:32:59 +02:00
kijai	9d8dfb0700	Update pipeline.py	2025-02-05 01:11:47 +02:00
Austin Mroz	f5f8ab2550	Support version calculation on AMD	2025-02-04 10:29:00 -06:00
kijai	67a4e7a650	Allow larger inputs with fast model ... Not sure if useful, but at least it doesn't error out unlike the normal model did with larger inputs than 530x530	2025-02-04 18:05:07 +02:00
kijai	17d964aa37	Support CublasOps for decoding ... https://github.com/aredden/torch-cublas-hgemm on a 4090 this is ~25% faster	2025-02-04 16:28:35 +02:00
kijai	1b7c0606e2	little tweaks	2025-02-03 20:01:32 +02:00
kijai	d618646a88	Update conditioner.py	2025-02-03 19:49:18 +02:00
kijai	2755e6b956	remove prints	2025-02-03 14:57:55 +02:00
kijai	046bb97fac	Support fast model ... https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-dit-v2-0-fast	2025-02-03 14:39:28 +02:00
kijai	2758f91a89	Add mask outputs to render nodes	2025-02-02 13:01:38 +02:00
kijai	dbd5f09c11	Merge branch 'pr/35'	2025-01-31 17:18:03 +02:00
kijai	9b6c5c12f9	Add torch 2.6.0 wheel for custom_rasterizer	2025-01-31 17:07:31 +02:00
Andrej	bc9e498c13	Update rasterizer_gpu.cu	2025-01-29 02:17:24 +01:00
Andrej	8bf6060bd9	Merge branch 'kijai:main' into main	2025-01-29 02:14:10 +01:00
kijai	bb441cbbed	decode multiview outputs one by one for less of a VRAM spike	2025-01-29 02:08:08 +02:00
Andrej	23c096572d	Update rasterizer_gpu.cu	2025-01-28 18:57:21 +01:00
kijai	5b19d811ab	Fix paint model .safetensors loading, add schedulers	2025-01-27 15:53:17 +02:00
kijai	a8f03c7b0a	Add Hy3DRenderSingleView -node	2025-01-26 17:02:29 +02:00
kijai	fb5a9d3229	expose ortho_scale	2025-01-26 03:14:07 +02:00
kijai	a887220a54	expose camera distance	2025-01-26 03:09:23 +02:00
kijai	d563280607	Separate VAE (old workflows need updating)	2025-01-26 02:48:37 +02:00
kijai	7e234a017e	make mask do something	2025-01-25 23:32:24 +02:00
kijai	e43874b483	Update vae.py	2025-01-25 20:32:44 +02:00
kijai	a86f12236e	support sageattn for mesh gen	2025-01-25 19:56:54 +02:00
kijai	9f59f92943	uncap face limit	2025-01-22 20:09:36 +02:00
kijai	75ad5e41eb	Add torch compile for main model	2025-01-22 10:27:21 +02:00
kijai	bba70eb67c	Add mesh_processor.py from upstream PR by MrForExample ... MrForExample https://github.com/Tencent/Hunyuan3D-2/pull/13	2025-01-22 10:05:57 +02:00
kijai	703edf2051	Use Accelerate to load the main model faster	2025-01-22 09:35:57 +02:00
kijai	7242e7e22e	more offloading for first stage	2025-01-22 08:54:10 +02:00
kijai	f609b2b512	update example, fix vae progressbar	2025-01-22 00:45:01 +02:00
kijai	6e12b7c3b4	Update rasterizer.h	2025-01-22 00:21:06 +02:00
kijai	f35870528f	update	2025-01-21 23:40:10 +02:00
kijai	2f262b32f2	update	2025-01-21 22:02:08 +02:00
kijai	4dbf46c580	Windows fixes	2025-01-21 21:36:02 +02:00
Jukka Seppänen	d194d4ee33	update	2025-01-21 21:07:49 +02:00
Jukka Seppänen	edadfb1b13	init	2025-01-21 20:01:16 +02:00