Image-to-3D
Hunyuan3D-2
Diffusers
Safetensors
English
Chinese
text-to-3d
ZeqiangLai commited on
Commit
4ea2fff
·
verified ·
1 Parent(s): 0798d34

Upload folder using huggingface_hub

Browse files
hunyuan3d-vae-v2-0-withencoder/config.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ target: hy3dgen.shapegen.models.ShapeVAE
2
+ params:
3
+ num_latents: 3072
4
+ embed_dim: 64
5
+ num_freqs: 8
6
+ point_feats: 4
7
+ include_pi: false
8
+ heads: 16
9
+ width: 1024
10
+ num_decoder_layers: 16
11
+ qkv_bias: false
12
+ qk_norm: true
13
+ scale_factor: 0.9990943042622529
14
+ geo_decoder_mlp_expand_ratio: 4
15
+ geo_decoder_downsample_ratio: 1
16
+ geo_decoder_ln_post: true
hunyuan3d-vae-v2-0-withencoder/model.fp16.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ec047ef88987198f94eaa16da5760c0ffa39df3d280fe5832d18d2e32176c4
3
+ size 655648555
hunyuan3d-vae-v2-0-withencoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ffbef849e750022298e88c146cf17f21713e0649aba005ee35ca696ce2b7b87
3
+ size 655539066