117 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Easymode	fc6b28cdde	Update nodes.py	2025-02-18 14:44:57 +00:00
kijai	f71b120662	Fix render singleview depth	2025-02-14 09:24:49 +02:00
Jukka Seppänen	1363f43870	Merge pull request #62 from AustinMroz/main ... Fix missed rename	2025-02-11 23:50:17 +02:00
Austin Mroz	90cf4e6285	Fix missed rename	2025-02-11 14:45:57 -06:00
kijai	b2a0f3d60c	Update nodes.py	2025-02-11 14:19:54 +02:00
kijai	ac28a60ac0	Update nodes.py	2025-02-07 22:34:52 +02:00
kijai	0c100bb092	Rename rename mesh slots to trimesh for clarity	2025-02-07 20:38:33 +02:00
Jukka Seppänen	4b3b5f69f3	bump version	2025-02-06 17:15:09 +02:00
Jukka Seppänen	8ea265419b	Merge pull request #45 from eltociear/patch-1 ... docs: update readme.md	2025-02-06 08:54:36 +02:00
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	d53712d7f9	licenses	2025-02-05 17:13:01 +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
kijai	2846bbf5cc	workaround to not always save the mesh for preview	2025-02-04 22:29:44 +02:00
Ikko Eltociear Ashimine	7995f31c3b	docs: update readme.md ... ran -> run	2025-02-05 02:43:14 +09:00
kijai	0e18f865eb	Update nodes.py	2025-02-04 19:22:20 +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	315dd9aa7a	Update nodes.py	2025-02-04 17:07:10 +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	a3d0277aed	Update hy3d_example_01.json	2025-02-04 15:31:50 +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	df4e4f7337	better bg color for tanget space normals	2025-02-03 16:54:28 +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	26a57e86b0	accept more upload formats	2025-02-02 14:06:10 +02:00
kijai	7bba1dd89a	Add upload mesh node	2025-02-02 13:57:03 +02:00
kijai	205be20e08	Add other export file formats	2025-02-02 13:15:14 +02:00
kijai	2758f91a89	Add mask outputs to render nodes	2025-02-02 13:01:38 +02:00
kijai	4000191965	Update nodes.py	2025-02-02 12:49:12 +02:00
kijai	9c69b6f4fd	bump version	2025-01-31 17:24:35 +02:00
kijai	6fb6cba50b	Update nodes.py	2025-01-31 17:24:05 +02:00
kijai	dbd5f09c11	Merge branch 'pr/35'	2025-01-31 17:18:03 +02:00
kijai	44ee33694b	Update nodes.py	2025-01-31 17:14:17 +02:00
kijai	9b6c5c12f9	Add torch 2.6.0 wheel for custom_rasterizer	2025-01-31 17:07:31 +02:00
kijai	4b3f123a66	minor tweaks to example workflow	2025-01-31 13:32:06 +02:00
kijai	9b29fe4bbe	Enable delight cfg_image, remove cfg_text as it doens't do anything ... cfg_text being 1.0 disables cfg completely, making cfg_image have no effect, cfg_text itself has no effect without prompt, changing this to allow just adjusting cfg_image as the sole guidance value	2025-01-31 02:04:49 +02:00
kijai	c899ce1a4d	Update nodes.py	2025-01-31 00:44:42 +02:00
kijai	f0d38b5b5d	Add Hy3DNvdiffrastRenderer -node	2025-01-30 15:37:12 +02:00
kijai	90935376d1	only download safetensors (if they exist)	2025-01-29 20:44:52 +02:00
kijai	f9b2465e6a	Add Hy3DFastSimplifyMesh, better mesh info node	2025-01-29 15:25:00 +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
kijai	448597bc89	Allow multiview render to return tangent space normals as well	2025-01-29 01:32:37 +02:00
Andrej	23c096572d	Update rasterizer_gpu.cu	2025-01-28 18:57:21 +01:00