MCPcopy Create free account

hub / github.com/bronyayang/Law_of_Vision_Representation_in_MLLMs / functions

Functions12,826 in github.com/bronyayang/Law_of_Vision_Representation_in_MLLMs

⨍ Functions 12,826◇ Types & classes 1,844↳ Endpoints 18
↓ 5 callersMethoddummy_sample
(self)
diffusers/tests/schedulers/test_schedulers.py:315
↓ 5 callersMethodenable_adapters
Enable adapters that are attached to the model. The model uses `self.active_adapters()` to retrieve the list of adapters to enable.
diffusers/src/diffusers/loaders/peft.py:145
↓ 5 callersMethodenable_vae_slicing
r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev
diffusers/src/diffusers/pipelines/pipeline_utils.py:1888
↓ 5 callersMethodencode_event
Encode an event to an index.
diffusers/src/diffusers/pipelines/deprecated/spectrogram_diffusion/midi_utils.py:185
↓ 5 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/stable_diffusion_diffedit/pipeline_stable_diffusion_diffedit.py:408
↓ 5 callersFunctionexpand2square
(pil_img, background_color)
llava/mm_utils.py:64
↓ 5 callersMethodexpand_tensor_or_array
Expand a tensor or array to a specified number of images.
diffusers/src/diffusers/pipelines/marigold/marigold_image_processing.py:32
↓ 5 callersFunctionextract_into_tensor
(a, t, x_shape)
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl.py:252
↓ 5 callersFunctionextract_into_tensor
(a, t, x_shape)
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py:409
↓ 5 callersFunctionextract_into_tensor
(a, t, x_shape)
diffusers/examples/consistency_distillation/train_lcm_distill_sdxl_wds.py:375
↓ 5 callersFunctionextract_into_tensor
(a, t, x_shape)
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py:396
↓ 5 callersFunctionextract_into_tensor
(a, t, x_shape)
diffusers/examples/consistency_distillation/train_lcm_distill_sd_wds.py:387
↓ 5 callersFunctionfetch_diffusers_config
(checkpoint)
diffusers/src/diffusers/loaders/single_file_utils.py:494
↓ 5 callersFunctionflip_keypoints
(keypoints, img_size, permute_list=None)
C_score/utils/utils_geoware.py:199
↓ 5 callersFunctionflow_warp
(feature, flow, mask=False, mode="bilinear", padding_mode="zeros")
diffusers/examples/community/rerender_a_video.py:83
↓ 5 callersMethodfreeze
Freeze the first several stages of the ResNet. Commonly used in fine-tuning. Layers that produce the same feature map spatial
C_score/model_utils/resnet.py:386
↓ 5 callersMethodfull_loop
(self, scheduler=None, **config)
diffusers/tests/schedulers/test_scheduler_deis.py:92
↓ 5 callersMethodgelu
(self, gate: torch.Tensor)
diffusers/src/diffusers/models/activations.py:81
↓ 5 callersFunctiongeneric_param_init_fn_
(module: nn.Module, init_fn_, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, flo
llava/model/language_model/mpt/param_init_fns.py:28
↓ 5 callersMethodget_crop_region
Finds a rectangular region that contains all masked ares in an image, and expands region to match the aspect ratio of the original im
diffusers/src/diffusers/image_processor.py:193
↓ 5 callersMethodget_dummy_components
(self, adapter_type, time_cond_proj_dim=None)
diffusers/tests/pipelines/stable_diffusion_adapter/test_stable_diffusion_adapter.py:60
↓ 5 callersMethodget_dummy_components
(self)
diffusers/tests/pipelines/controlnet/test_controlnet_inpaint_sdxl.py:76
↓ 5 callersMethodget_dummy_components
(self)
diffusers/tests/pipelines/pixart_sigma/test_pixart.py:54
↓ 5 callersMethodget_dummy_components
(self, time_cond_proj_dim=None)
diffusers/tests/pipelines/stable_diffusion/test_stable_diffusion_inpaint.py:405
↓ 5 callersMethodget_dummy_components
(self)
diffusers/tests/pipelines/stable_cascade/test_stable_cascade_combined.py:135
↓ 5 callersMethodget_dummy_inputs
(self, device, seed=0, height=64, width=64, num_images=1)
diffusers/tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_adapter.py:271
↓ 5 callersMethodget_dummy_inputs
(self, device, seed=0)
diffusers/tests/pipelines/controlnet/test_controlnet_sdxl.py:793
↓ 5 callersMethodget_dummy_inputs
(self, seed=0)
diffusers/tests/pipelines/stable_diffusion/test_onnx_stable_diffusion_upscale.py:49
↓ 5 callersMethodget_dummy_inputs
(self, device, seed=0)
diffusers/tests/pipelines/stable_diffusion/test_stable_diffusion_instruction_pix2pix.py:119
↓ 5 callersMethodget_dummy_inputs
(self, device, seed=0)
diffusers/tests/pipelines/wuerstchen/test_wuerstchen_prior.py:144
↓ 5 callersMethodget_dummy_inputs_pipe
(self, device, seed=0)
diffusers/tests/pipelines/test_pipelines_common.py:634
↓ 5 callersMethodget_image_processor
(self, repo_id)
diffusers/tests/pipelines/ip_adapters/test_ip_adapter_stable_diffusion.py:71
↓ 5 callersFunctionget_img_result
(all_results, cls=None, geo=False, flip=False, az=None)
C_score/utils/eval_spair.py:354
↓ 5 callersMethodget_inputs
(self, device="cpu", dtype=torch.float32, seed=0)
diffusers/tests/pipelines/stable_diffusion_2/test_stable_diffusion_depth.py:391
↓ 5 callersMethodget_inputs
(self, device, generator_device="cpu", dtype=torch.float32, seed=0)
diffusers/tests/pipelines/stable_diffusion/test_stable_diffusion.py:1376
↓ 5 callersMethodget_list_adapters
Gets the current list of all available adapters in the pipeline.
diffusers/src/diffusers/loaders/lora.py:1105
↓ 5 callersMethodget_output_embeddings
(self)
llava/model/language_model/mpt/modeling_mpt.py:261
↓ 5 callersFunctionget_params_to_save
(params)
diffusers/examples/textual_inversion/textual_inversion_flax.py:361
↓ 5 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_edm_euler.py:17
↓ 5 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_heun.py:13
↓ 5 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_sasolver.py:15
↓ 5 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_ddim_parallel.py:26
↓ 5 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_lms.py:13
↓ 5 callersMethodget_scheduler_config
(self)
diffusers/tests/schedulers/test_scheduler_flax.py:63
↓ 5 callersMethodget_sd_image
(self, seed=0, shape=(4, 3, 512, 512), fp16=False)
diffusers/tests/models/autoencoders/test_models_vae.py:806
↓ 5 callersMethodget_sd_vae_model
(self, model_id="cross-attention/asymmetric-autoencoder-kl-x-1-5", fp16=False)
diffusers/tests/models/autoencoders/test_models_vae.py:811
↓ 5 callersMethodget_vq_and_discriminator_configs
(self, tmpdir)
diffusers/examples/vqgan/test_vqgan.py:81
↓ 5 callersFunctionget_word_inds
(text: str, word_place: int, tokenizer)
diffusers/examples/community/pipeline_prompt2prompt.py:1240
↓ 5 callersMethodhas_test_docs
Whether the task has a test set
llava/eval/lmms-eval/lmms_eval/api/task.py:277
↓ 5 callersFunctioninit_empty_weights
Meta initialization context manager. A context manager under which models are initialized with all parameters on the meta device, therefore c
llava/model/language_model/mpt/meta_init_context.py:6
↓ 5 callersFunctionis_scipy_available
()
diffusers/src/diffusers/utils/import_utils.py:374
↓ 5 callersFunctionis_torchsde_available
()
diffusers/src/diffusers/utils/import_utils.py:418
↓ 5 callersFunctionload_checkpoint_to_model
(checkpoint, model, strict=False)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:1033
↓ 5 callersMethodmodel
(sample, t, *args)
diffusers/tests/schedulers/test_schedulers.py:359
↓ 5 callersFunctionmultiply_range
(start_position, multiplier)
diffusers/examples/community/lpw_stable_diffusion_onnx.py:120
↓ 5 callersFunctionmultiply_range
(start_position, multiplier)
diffusers/examples/community/lpw_stable_diffusion_xl.py:105
↓ 5 callersFunctionmultiply_range
(start_position, multiplier)
diffusers/examples/community/lpw_stable_diffusion.py:93
↓ 5 callersMethodnumpy_to_pt
Convert a NumPy image to a PyTorch tensor.
diffusers/src/diffusers/pipelines/marigold/marigold_image_processing.py:59
↓ 5 callersFunctiononnx_export
( model, model_args: tuple, output_path: Path, ordered_input_names, output_names, dyna
diffusers/scripts/convert_stable_diffusion_controlnet_to_onnx.py:187
↓ 5 callersFunctiononnx_export
( model, model_args: tuple, output_path: Path, ordered_input_names, output_names, dyna
diffusers/scripts/convert_stable_diffusion_checkpoint_to_onnx.py:31
↓ 5 callersMethodprepare_init_args_and_inputs_for_common
(self)
diffusers/tests/models/unets/test_models_unet_3d_condition.py:60
↓ 5 callersMethodpreprocess_video
r""" Preprocesses input video(s). Args: video (`List[PIL.Image]`, `List[List[PIL.Image]]`, `torch.Tensor`, `np.array`, `L
diffusers/src/diffusers/video_processor.py:28
↓ 5 callersFunctionprior
(*, args, checkpoint_map_location)
diffusers/scripts/convert_shap_e_to_diffusers.py:930
↓ 5 callersMethodpt_to_numpy
Convert a PyTorch tensor to a NumPy image.
diffusers/src/diffusers/image_processor.py:144
↓ 5 callersMethodpt_to_numpy
Convert a PyTorch tensor to a NumPy image.
diffusers/src/diffusers/pipelines/marigold/marigold_image_processing.py:51
↓ 5 callersFunctionrearrange_dims
(tensor: torch.Tensor)
diffusers/src/diffusers/models/resnet.py:377
↓ 5 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_original_audioldm2_to_diffusers.py:65
↓ 5 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_versatile_diffusion_to_diffusers.py:106
↓ 5 callersMethodresize_antialias
( image: torch.Tensor, size: Tuple[int, int], mode: str, is_aa: Optional[bool] = None )
diffusers/src/diffusers/pipelines/marigold/marigold_image_processing.py:74
↓ 5 callersFunctionrunEngine
(engine, feed_dict, stream)
diffusers/examples/community/stable_diffusion_tensorrt_inpaint.py:411
↓ 5 callersFunctionrunEngine
(engine, feed_dict, stream)
diffusers/examples/community/stable_diffusion_tensorrt_img2img.py:411
↓ 5 callersMethodrun_safety_checker
(self, image, device, dtype)
diffusers/examples/community/fresco_v2v.py:1675
↓ 5 callersMethodsave_lora_weights
r""" Save the LoRA parameters corresponding to the UNet and text encoder. Arguments: save_directory (`str` or `os.PathLik
diffusers/src/diffusers/loaders/lora.py:627
↓ 5 callersMethodsave_model
(self, output_dir: Optional[str] = None, _internal_call: bool = False)
llava/train/llava_trainer.py:389
↓ 5 callersMethodset_image_to_text_mode
r"""Manually set the generation mode to image-conditioned text generation.
diffusers/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py:260
↓ 5 callersMethodset_lora_layer
(self, lora_layer: Optional[LoRAConv2dLayer])
diffusers/src/diffusers/models/lora.py:311
↓ 5 callersMethodset_text_to_image_mode
r"""Manually set the generation mode to text-conditioned image generation.
diffusers/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py:256
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_original_audioldm2_to_diffusers.py:54
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_svd_to_diffusers.py:213
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_versatile_diffusion_to_diffusers.py:96
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_original_audioldm_to_diffusers.py:45
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_zero123_to_diffusers.py:198
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_original_musicldm_to_diffusers.py:46
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:71
↓ 5 callersMethodsimulate_backprop
(self, unet)
diffusers/tests/others/test_ema.py:54
↓ 5 callersFunctionto_np
(tensor)
diffusers/tests/pipelines/animatediff/test_animatediff_sdxl.py:28
↓ 5 callersFunctionupdate_unet_attention_ldm_to_diffusers
(ldm_keys, new_checkpoint, checkpoint, mapping)
diffusers/src/diffusers/loaders/single_file_utils.py:753
↓ 5 callersFunctionupdate_unet_resnet_ldm_to_diffusers
(ldm_keys, new_checkpoint, checkpoint, mapping=None)
diffusers/src/diffusers/loaders/single_file_utils.py:738
↓ 5 callersMethodwrite_lora_layers
( state_dict: Dict[str, torch.Tensor], save_directory: str, is_main_process: bool,
diffusers/src/diffusers/loaders/lora.py:692
↓ 5 callersFunctionzero_module
(module)
diffusers/src/diffusers/models/controlnet.py:868
↓ 4 callersMethod__init__
( self, in_channels: int, out_channels: int, prev_output_channel: int,
diffusers/src/diffusers/pipelines/audioldm2/modeling_audioldm2.py:1357
↓ 4 callersMethod__init__
(self, c, c_skip=0, kernel_size=3, dropout=0.0)
diffusers/src/diffusers/pipelines/wuerstchen/modeling_wuerstchen_common.py:29
↓ 4 callersMethod__init__
( self, in_features: int, out_features: int, rank: int = 4, network_al
diffusers/src/diffusers/models/lora.py:196
↓ 4 callersMethod__init__
( self, channels, num_res_blocks: int, hidden_size, hidden_dropout,
diffusers/src/diffusers/models/unets/uvit_2d.py:308
↓ 4 callersMethod__init__
(self, unet, scheduler)
diffusers/examples/community/dps_pipeline.py:44
↓ 4 callersMethod__init__
Extra keyword arguments supported in addition to those in `torch.nn.Conv2d`: Args: norm (nn.Module, optional): a normaliz
C_score/model_utils/resnet.py:124
↓ 4 callersMethod_apply_free_init
( self, latents: torch.Tensor, free_init_iteration: int, num_inference_steps:
diffusers/src/diffusers/pipelines/free_init_utils.py:138
↓ 4 callersMethod_combine
r""" Combines a latent iamge img_vae of shape (B, C, H, W) and a CLIP-embedded image img_clip of shape (B, 1, clip_img_dim) into a sin
diffusers/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py:790
↓ 4 callersMethod_compute_loss
Computes the attend-and-excite loss using the maximum attention value for each token.
diffusers/examples/community/pipeline_stable_diffusion_boxdiff.py:1151
↓ 4 callersMethod_encode_prompt
(self, input_ids, attention_mask, text_encoder_use_attention_mask=False)
diffusers/examples/community/sde_drag.py:348
← previousnext →601–700 of 12,826, ranked by callers