Functions — github.com/Stable-X/ComfyUI-Hi3DGen

hub / github.com/Stable-X/ComfyUI-Hi3DGen / functions

Functions333 in github.com/Stable-X/ComfyUI-Hi3DGen

⨍ Functions 333◇ Types & classes 71

Methodforward

(self, x: sp.SparseTensor, t: torch.Tensor, cond: torch.Tensor)

trellis/models/structured_latent_flow.py:234

Methodforward

(self, x: sp.SparseTensor)

trellis/models/structured_latent_vae/base.py:110

Methodforward

Apply the block to a Tensor, conditioned on a timestep embedding. Args: x: an [N x C x ...] Tensor of features.

trellis/models/structured_latent_vae/decoder_mesh.py:54

Methodforward

(self, x: sp.SparseTensor)

trellis/models/structured_latent_vae/decoder_mesh.py:161

Methodforward

(self, x: sp.SparseTensor, sample_posterior=True, return_raw=False)

trellis/models/structured_latent_vae/encoder.py:54

Methodforward

The [`ControlNetVAEModel`] forward method. Args: sample (`torch.Tensor`): The noisy input tensor.

stablex/controlnetvae.py:24

Functionfrom_pretrained

Load a pipeline from a model folder or a Hugging Face model hub. Args: path: The path to the model. Can be either local path or

trellis/pipelines/__init__.py:5

Functionfrom_pretrained

Load a pretrained model. Args: path (str): Full path to model file or HuggingFace repo ID with model name

trellis/models/__init__.py:34

Methodfrom_pretrained

Load a pretrained model. Args: path (str): The path to the model. Can be either local path or a Hugging Face reposit

trellis/pipelines/trellis_image_to_3d.py:59

Methodfull

(aabb, dim, value, dtype=torch.float32, device=None)

trellis/modules/sparse/basic.py:284

Methodimage_to_3d

( self, model: TrellisImageTo3DPipeline, mode: str, images: torch.Tensor,

IF_Trellis.py:199

Functionindent

Indent a string.

trellis/utils/general_utils.py:179

Methodinitialize_weights

(self)

trellis/models/structured_latent_vae/base.py:101

Methodlayout

(self)

trellis/modules/sparse/basic.py:144

Methodload_model

Load and configure the TRELLIS pipeline. This is typically the main function invoked by ComfyUI at node execution time.

IF_TrellisCheckpointLoader.py:126

Methodload_model_components

Loads individual model components.

trellis_model_manager.py:155

(images, nrow=None, ncol=None, aspect_ratio=None)

trellis/utils/general_utils.py:118

Functionmodulate

(x, shift, scale)

trellis/modules/utils.py:53

Methodprocess

(self, pipeline, image, processing_resolution,controlnet_strength, seed)

StableXWrapper.py:111

Methodprogress_bar

(self, iterable=None, total=None, desc=None, leave=True)

stablex/pipeline_yoso.py:310

Functionrasterize_triangle_faces

Rasterize a mesh with vertex attributes.

trellis/utils/_rasterization.py:9

Methodretrieve_latents

(encoder_output)

stablex/pipeline_yoso.py:537

Functionrtol

Relative tolerance.

trellis/utils/general_utils.py:171

Methodsample

Generate samples from the model using Euler method. Args: model: The model to sample from. nois

trellis/pipelines/samplers/flow_euler.py:125

Methodsample

Generate samples from the model using Euler method. Args: model: The model to sample from. nois

trellis/pipelines/samplers/flow_euler.py:165

Functionsave_image_with_notes

Save an image with notes.

trellis/utils/general_utils.py:150

Functionscale_module

Scale the parameters of a module and return it.

trellis/modules/utils.py:44

Functionset_debug

Set debug mode

trellis/backend_config.py:169

Methodshape

(self)

trellis/modules/sparse/basic.py:137

Functionsparse_batch_op

Broadcast a 1D tensor to a sparse tensor along the batch dimension then perform an operation. Args: input (torch.Tensor): 1D

trellis/modules/sparse/basic.py:415

Functionsparse_cat

Concatenate a list of sparse tensors. Args: inputs (List[SparseTensor]): List of sparse tensors to concatenate.

trellis/modules/sparse/basic.py:427

Functionsphere_hammersley_sequence

(n, num_samples, offset=(0, 0), remap=False)

trellis/utils/random_utils.py:22

← previous301–333 of 333, ranked by callers