|
model:
|
|
target: hy3dgen.shapegen.models.Hunyuan3DDiT
|
|
params:
|
|
in_channels: 64
|
|
context_in_dim: 1536
|
|
hidden_size: 1024
|
|
mlp_ratio: 4.0
|
|
num_heads: 16
|
|
depth: 16
|
|
depth_single_blocks: 32
|
|
axes_dim: [ 64 ]
|
|
theta: 10000
|
|
qkv_bias: True
|
|
|
|
vae:
|
|
target: hy3dgen.shapegen.models.ShapeVAE
|
|
params:
|
|
num_latents: 3072
|
|
embed_dim: 64
|
|
num_freqs: 8
|
|
include_pi: false
|
|
heads: 16
|
|
width: 1024
|
|
num_decoder_layers: 16
|
|
qkv_bias: false
|
|
qk_norm: true
|
|
scale_factor: 0.9990943042622529
|
|
|
|
conditioner:
|
|
target: hy3dgen.shapegen.models.SingleImageEncoder
|
|
params:
|
|
main_image_encoder:
|
|
type: DinoImageEncoder
|
|
kwargs:
|
|
config:
|
|
attention_probs_dropout_prob: 0.0
|
|
drop_path_rate: 0.0
|
|
hidden_act: gelu
|
|
hidden_dropout_prob: 0.0
|
|
hidden_size: 1536
|
|
image_size: 518
|
|
initializer_range: 0.02
|
|
layer_norm_eps: 1.e-6
|
|
layerscale_value: 1.0
|
|
mlp_ratio: 4
|
|
model_type: dinov2
|
|
num_attention_heads: 24
|
|
num_channels: 3
|
|
num_hidden_layers: 40
|
|
patch_size: 14
|
|
qkv_bias: true
|
|
torch_dtype: float32
|
|
use_swiglu_ffn: true
|
|
image_size: 518
|
|
|
|
scheduler:
|
|
target: hy3dgen.shapegen.schedulers.FlowMatchEulerDiscreteScheduler
|
|
params:
|
|
num_train_timesteps: 1000
|
|
|
|
image_processor:
|
|
target: hy3dgen.shapegen.preprocessors.ImageProcessorV2
|
|
params:
|
|
size: 512
|
|
border_ratio: 0.15
|
|
|
|
pipeline:
|
|
target: hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
|
|
|
