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
↓ 2 callersFunctionget_warped_and_mask
(flow_model, image1, image2, image3=None, pixel_consistency=False, device=None)
diffusers/examples/community/rerender_a_video.py:115
↓ 2 callersFunctionglobal_version_update
Update the version in all needed files.
diffusers/utils/release.py:61
↓ 2 callersFunctiongrad_layer_wrt_loss
(loss, layer)
diffusers/examples/vqgan/train_vqgan.py:119
↓ 2 callersMethodhas_test_docs
(self)
llava/eval/lmms-eval/lmms_eval/api/task.py:739
↓ 2 callersMethodhas_validation_docs
(self)
llava/eval/lmms-eval/lmms_eval/api/task.py:733
↓ 2 callersFunctionhttp_user_agent
Formats a user-agent string with basic info about a request.
diffusers/src/diffusers/utils/hub_utils.py:75
↓ 2 callersFunctionimport_flax_or_no_model
(module, class_name)
diffusers/src/diffusers/pipelines/pipeline_flax_utils.py:74
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/dreambooth/train_dreambooth_lora_sdxl.py:240
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/text_to_image/train_text_to_image_lora_sdxl.py:166
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/text_to_image/train_text_to_image_sdxl.py:114
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/t2i_adapter/train_t2i_adapter_sdxl.py:179
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py:231
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/controlnet/train_controlnet_sdxl.py:195
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/instruct_pix2pix/train_instruct_pix2pix_sdxl.py:123
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl.py:258
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/consistency_distillation/train_lcm_distill_sdxl_wds.py:453
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py:430
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/research_projects/diffusion_orpo/train_diffusion_orpo_sdxl_lora_wds.py:71
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/research_projects/diffusion_orpo/train_diffusion_orpo_sdxl_lora.py:73
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth_lora_sdxl.py:239
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_lora_sdxl.py:119
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_sdxl.py:112
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/research_projects/diffusion_dpo/train_diffusion_dpo_sdxl.py:73
↓ 2 callersFunctionimport_model_class_from_model_name_or_path
( pretrained_model_name_or_path: str, revision: str, subfolder: str = "text_encoder" )
diffusers/examples/research_projects/controlnet/train_controlnet_webdataset.py:419
↓ 2 callersFunctioninclude_path
(task_dir)
llava/eval/lmms-eval/lmms_eval/tasks/__init__.py:100
↓ 2 callersFunctioninclude_task_folder
Calling this function
llava/eval/lmms-eval/lmms_eval/tasks/__init__.py:67
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_lms_discrete.py:304
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_sde.py:202
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py:354
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_consistency_models.py:295
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py:322
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_deis_multistep.py:642
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_edm_euler.py:249
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_edm_dpmsolver_multistep.py:562
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_k_dpm_2_discrete.py:289
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py:889
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_unipc_multistep.py:790
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py:860
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
diffusers/src/diffusers/schedulers/scheduling_heun_discrete.py:152
↓ 2 callersMethodinfer_shapes
(self, return_onnx=False)
diffusers/examples/community/stable_diffusion_tensorrt_inpaint.py:215
↓ 2 callersMethodinfer_shapes
(self, return_onnx=False)
diffusers/examples/community/stable_diffusion_tensorrt_txt2img.py:200
↓ 2 callersMethodinfer_shapes
(self, return_onnx=False)
diffusers/examples/community/stable_diffusion_tensorrt_img2img.py:215
↓ 2 callersMethodinit_attn_processors
( self, mask, token_idx, use_painta=True, use_rasg=True, paint
diffusers/examples/community/hd_painter.py:406
↓ 2 callersMethodinit_run
(self)
llava/eval/lmms-eval/lmms_eval/logging_utils.py:89
↓ 2 callersMethodinitialize_vision_modules
(self, model_args, fsdp=None)
llava/model/llava_arch.py:108
↓ 2 callersMethodinitialize_vision_tokenizer
(self, model_args, tokenizer)
llava/model/llava_arch.py:481
↓ 2 callersFunctionis_clip_sd3_model
(checkpoint)
diffusers/src/diffusers/loaders/single_file_utils.py:379
↓ 2 callersMethodis_interval
(self, expr)
llava/eval/lmms-eval/lmms_eval/tasks/olympiadbench/olympiadbench_evals.py:124
↓ 2 callersFunctionis_k_diffusion_version
Args: Compares the current k-diffusion version to a given reference with an operation. operation (`str`): A string repres
diffusers/src/diffusers/utils/import_utils.py:721
↓ 2 callersFunctionis_none
(value)
llava/eval/model_vqa_mmbench.py:33
↓ 2 callersFunctionis_open_clip_sd3_model
(checkpoint)
diffusers/src/diffusers/loaders/single_file_utils.py:400
↓ 2 callersFunctionis_open_clip_sdxl_model
(checkpoint)
diffusers/src/diffusers/loaders/single_file_utils.py:393
↓ 2 callersFunctionis_open_clip_sdxl_refiner_model
(checkpoint)
diffusers/src/diffusers/loaders/single_file_utils.py:407
↓ 2 callersFunctionis_opencv_available
()
diffusers/src/diffusers/utils/import_utils.py:370
↓ 2 callersFunctionis_safetensors_available
()
diffusers/src/diffusers/utils/import_utils.py:438
↓ 2 callersFunctionis_torchvision_available
()
diffusers/src/diffusers/utils/import_utils.py:430
↓ 2 callersFunctionis_valid_url
(url)
diffusers/src/diffusers/loaders/single_file_utils.py:268
↓ 2 callersFunctionjax_cosine_distance
(emb_1, emb_2, eps=1e-12)
diffusers/src/diffusers/pipelines/stable_diffusion/safety_checker_flax.py:25
↓ 2 callersMethodjudge
(self, expression1, expression2, precision=1e-8)
llava/eval/lmms-eval/lmms_eval/tasks/olympiadbench/olympiadbench_evals.py:74
↓ 2 callersFunctionkeep_doc_examples_only
Remove everything from the code content except the doc examples (used to determined if a diff should trigger doc tests or not). Args:
diffusers/utils/tests_fetcher.py:138
↓ 2 callersMethodlayers
(self)
diffusers/examples/community/stable_diffusion_comparison.py:84
↓ 2 callersFunctionlerp
r""" Linear Interpolation between two tensors. Args: v0 (`torch.Tensor`): First tensor. v1 (`torch.Tensor`): Second tensor.
diffusers/examples/community/pipeline_animatediff_img2video.py:70
↓ 2 callersMethodload
(self)
diffusers/examples/community/stable_diffusion_tensorrt_txt2img.py:143
↓ 2 callersMethodload
(self)
diffusers/examples/community/stable_diffusion_tensorrt_img2img.py:158
↓ 2 callersFunctionload_and_prepare_data
Load and prepare dataset for training. Parameters: - PASCAL_TRAIN: Flag to indicate if training on PASCAL dataset. - AP10K_TRAIN: Fl
C_score/utils/utils_dataset.py:37
↓ 2 callersFunctionload_ap10k_data
(path="data/ap-10k", size=840, category='cat', split='test', subsample=20)
C_score/utils/utils_dataset.py:151
↓ 2 callersFunctionload_config
(config_path)
C_score/utils/logger.py:8
↓ 2 callersFunctionload_eval_data
(args, path, category, split)
C_score/utils/utils_dataset.py:115
↓ 2 callersMethodload_image_canonical
( image: Union[torch.Tensor, np.ndarray, Image.Image], device: torch.device = torch.device("cp
diffusers/src/diffusers/pipelines/marigold/marigold_image_processing.py:144
↓ 2 callersFunctionload_model
(config_path="Panoptic/odise_label_coco_50e.py", seed=42, diffusion_ver="v1-3", image_size=1024, num_timesteps
C_score/model_utils/extractor_sd.py:163
↓ 2 callersMethodload_model
Loads an ONNX Inference session with an ExecutionProvider. Default provider is `CPUExecutionProvider` Arguments: path (`
diffusers/src/diffusers/pipelines/onnx_utils.py:64
↓ 2 callersFunctionload_pascal_data
(path="data/PF-dataset-PASCAL", size=256, category='cat', split='test', subsample=None)
C_score/utils/utils_dataset.py:304
↓ 2 callersMethodload_pretrained_weights
(self, pretrained_dict)
C_score/model_utils/projection_network.py:73
↓ 2 callersFunctionload_prior_checkpoint_to_model
(checkpoint, model)
diffusers/scripts/convert_shap_e_to_diffusers.py:991
↓ 2 callersFunctionload_single_file_checkpoint
( pretrained_model_link_or_path, resume_download=False, force_download=False, proxies=None,
diffusers/src/diffusers/loaders/single_file_utils.py:307
↓ 2 callersFunctionload_spair_data
(path1, path2, size=256)
C_score/utils/eval_spair.py:15
↓ 2 callersFunctionload_spair_data
(path="data/SPair-71k", size=256, category='cat', split='test', subsample=None)
C_score/utils/utils_dataset.py:208
↓ 2 callersFunctionload_tensors
(subfolder)
llava/eval/language_align.py:21
↓ 2 callersFunctionload_text_encoders
(class_one, class_two, class_three)
diffusers/examples/dreambooth/train_dreambooth_sd3.py:136
↓ 2 callersFunctionload_text_encoders
(class_one, class_two, class_three)
diffusers/examples/dreambooth/train_dreambooth_lora_sd3.py:140
↓ 2 callersMethodlog_Q_t_transitioning_to_known_class
Calculates the log probabilities of the rows from the (cumulative or non-cumulative) transition matrix for each latent pixel in `x_t`
diffusers/src/diffusers/schedulers/scheduling_vq_diffusion.py:356
↓ 2 callersFunctionlog_geo_stats
Log the geo-aware statistics. Parameters: - geo_aware, geo_aware_count: Lists to hold geo-aware counts. - pcks_geo, pcks_geo_05, pck
C_score/utils/logger.py:75
↓ 2 callersFunctionlog_grad_norm
(model, accelerator, global_step)
diffusers/examples/vqgan/train_vqgan.py:195
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, pipeline_args, epoch, is_final_validation=False, )
diffusers/examples/dreambooth/train_dreambooth_lora_sdxl.py:177
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, pipeline_args, epoch, is_final_validation=False, )
diffusers/examples/dreambooth/train_dreambooth_sd3.py:149
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, pipeline_args, epoch, is_final_validation=False, )
diffusers/examples/dreambooth/train_dreambooth_lora.py:119
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, pipeline_args, epoch, is_final_validation=False, )
diffusers/examples/dreambooth/train_dreambooth_lora_sd3.py:153
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, epoch, is_final_validation=False, )
diffusers/examples/text_to_image/train_text_to_image_lora.py:105
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, epoch, is_final_validation=False, )
diffusers/examples/text_to_image/train_text_to_image_lora_sdxl.py:125
↓ 2 callersFunctionlog_validation
(pipeline, pipeline_params, controlnet_params, tokenizer, args, rng, weight_dtype)
diffusers/examples/controlnet/train_controlnet_flax.py:68
↓ 2 callersFunctionlog_validation
( vae, text_encoder, tokenizer, unet, controlnet, args, accelerator, weight_dtype, step, is_final_validati
diffusers/examples/controlnet/train_controlnet.py:79
↓ 2 callersFunctionlog_validation
(vae, unet, controlnet, args, accelerator, weight_dtype, step, is_final_validation=False)
diffusers/examples/controlnet/train_controlnet_sdxl.py:71
↓ 2 callersFunctionlog_validation
(pipeline, args, accelerator, generator, global_step, is_final_validation=False)
diffusers/examples/instruct_pix2pix/train_instruct_pix2pix_sdxl.py:74
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, generator, )
diffusers/examples/instruct_pix2pix/train_instruct_pix2pix.py:70
↓ 2 callersFunctionlog_validation
(vae, args, accelerator, weight_dtype, step, unet=None, is_final_validation=False)
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl.py:106
↓ 2 callersFunctionlog_validation
(vae, unet, args, accelerator, weight_dtype, step, name="target")
diffusers/examples/consistency_distillation/train_lcm_distill_sdxl_wds.py:240
↓ 2 callersFunctionlog_validation
(vae, unet, args, accelerator, weight_dtype, step, name="target")
diffusers/examples/consistency_distillation/train_lcm_distill_sd_wds.py:222
↓ 2 callersFunctionlog_validation
(args, unet, vae, accelerator, weight_dtype, epoch, is_final_validation=False)
diffusers/examples/research_projects/diffusion_orpo/train_diffusion_orpo_sdxl_lora_wds.py:91
↓ 2 callersFunctionlog_validation
(args, unet, vae, accelerator, weight_dtype, epoch, is_final_validation=False)
diffusers/examples/research_projects/diffusion_orpo/train_diffusion_orpo_sdxl_lora.py:93
↓ 2 callersFunctionlog_validation
( pipeline, args, accelerator, pipeline_args, epoch, is_final_validation=False, )
diffusers/examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth_lora_sdxl.py:178
← previousnext →1,701–1,800 of 12,826, ranked by callers