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
↓ 4 callersMethodget_empty_store
()
diffusers/examples/community/pipeline_stable_diffusion_boxdiff.py:202
↓ 4 callersMethodget_guidance_scale_embedding
See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298 Args: timeste
diffusers/examples/community/gluegen.py:525
↓ 4 callersFunctionget_indent
Returns the indent in given line (as string).
diffusers/utils/custom_init_isort.py:59
↓ 4 callersMethodget_inputs
(self, device, generator_device="cpu", dtype=torch.float32, seed=0)
diffusers/tests/single_file/test_stable_diffusion_single_file.py:44
↓ 4 callersMethodget_inputs
(self, device="cpu", dtype=torch.float32, seed=0)
diffusers/tests/pipelines/stable_diffusion_2/test_stable_diffusion_depth.py:534
↓ 4 callersMethodget_inputs
(self, device, seed=0, generate_latents=False)
diffusers/tests/pipelines/unidiffuser/test_unidiffuser.py:593
↓ 4 callersMethodget_inputs
(self, seed=0, get_fixed_latents=False, device="cpu", dtype=torch.float32, shape=(1, 3, 64, 64))
diffusers/tests/pipelines/consistency_models/test_consistency_models.py:183
↓ 4 callersMethodget_inputs
(self, seed=0)
diffusers/tests/pipelines/stable_diffusion_panorama/test_stable_diffusion_panorama.py:275
↓ 4 callersMethodget_inputs
(self, device, generator_device="cpu", dtype=torch.float32, seed=0)
diffusers/tests/pipelines/stable_diffusion/test_stable_diffusion_img2img.py:671
↓ 4 callersMethodget_inputs
(self, device, generator_device="cpu", dtype=torch.float32, seed=0)
diffusers/tests/pipelines/stable_diffusion/test_stable_diffusion_inpaint.py:1023
↓ 4 callersFunctionget_logger
(output_file)
C_score/utils/logger.py:13
↓ 4 callersMethodget_minmax_dims
(self, batch_size, image_height, image_width, static_batch, static_shape)
diffusers/examples/community/stable_diffusion_tensorrt_inpaint.py:282
↓ 4 callersMethodget_minmax_dims
(self, batch_size, image_height, image_width, static_batch, static_shape)
diffusers/examples/community/stable_diffusion_tensorrt_img2img.py:282
↓ 4 callersFunctionget_module_dependencies
Refines the result of `extract_imports` to remove subfolders and get a proper list of module filenames: if a file as an import `from utils im
diffusers/utils/tests_fetcher.py:560
↓ 4 callersFunctionget_norm
Args: norm (str or callable): either one of BN, SyncBN, FrozenBN, GN; or a callable that takes a channel number and returns
C_score/model_utils/resnet.py:12
↓ 4 callersFunctionget_params_to_save
(params)
diffusers/examples/research_projects/multi_token_textual_inversion/textual_inversion_flax.py:348
↓ 4 callersFunctionget_patch_descriptors
(args, aggre_net, num_patches, files, pair_idx, flip=False, flip2=False, img1=None, img2=None, device='cuda')
C_score/pck_train_two.py:55
↓ 4 callersFunctionget_patch_descriptors
(args, aggre_net, num_patches, files, pair_idx, flip=False, flip2=False, img1=None, img2=None, device='cuda')
C_score/pck_train.py:46
↓ 4 callersFunctionget_patch_idx
(scale_factor, num_patches, img1_y, img1_x)
C_score/utils/utils_losses.py:109
↓ 4 callersFunctionget_peft_kwargs
(rank_dict, network_alpha_dict, peft_state_dict, is_unet=True)
diffusers/src/diffusers/utils/peft_utils.py:150
↓ 4 callersFunctionget_predicted_original_sample
(model_output, timesteps, sample, prediction_type, alphas, sigmas)
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl.py:215
↓ 4 callersFunctionget_predicted_original_sample
(model_output, timesteps, sample, prediction_type, alphas, sigmas)
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py:372
↓ 4 callersFunctionget_predicted_original_sample
(model_output, timesteps, sample, prediction_type, alphas, sigmas)
diffusers/examples/consistency_distillation/train_lcm_distill_sdxl_wds.py:338
↓ 4 callersFunctionget_predicted_original_sample
(model_output, timesteps, sample, prediction_type, alphas, sigmas)
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py:359
↓ 4 callersFunctionget_predicted_original_sample
(model_output, timesteps, sample, prediction_type, alphas, sigmas)
diffusers/examples/consistency_distillation/train_lcm_distill_sd_wds.py:350
↓ 4 callersFunctionget_prompts_tokens_with_weights
Get prompt token ids and weights, this function works for both prompt and negative prompt Args: pipe (CLIPTokenizer) A C
diffusers/examples/community/lpw_stable_diffusion_xl.py:153
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_dpm_sde.py:14
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_kdpm2_discrete.py:13
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_unclip.py:12
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_kdpm2_ancestral.py:13
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_ddim.py:12
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_score_sde_ve.py:47
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_ipndm.py:14
↓ 4 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_euler_ancestral.py:13
↓ 4 callersMethodget_timesteps
(self, num_inference_steps, strength, device)
diffusers/examples/community/fresco_v2v.py:1946
↓ 4 callersFunctiongroup_tokens_and_weights
Produce tokens and weights in groups and pad the missing tokens Args: token_ids (list) The token ids from tokenizer
diffusers/examples/community/lpw_stable_diffusion_xl.py:203
↓ 4 callersMethodhas_validation_docs
Whether the task has a validation set
llava/eval/lmms-eval/lmms_eval/api/task.py:272
↓ 4 callersMethodinvert
r""" The function to the pipeline for image inversion as described by the [LEDITS++ Paper](https://arxiv.org/abs/2301.12247). If the s
diffusers/src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py:1199
↓ 4 callersFunctionis_clip_model
(checkpoint)
diffusers/src/diffusers/loaders/single_file_utils.py:365
↓ 4 callersFunctionis_non_str_iterable
(obj)
llava/eval/lmms-eval/lmms_eval/api/metrics.py:336
↓ 4 callersFunctionis_open_clip_model
(checkpoint)
diffusers/src/diffusers/loaders/single_file_utils.py:386
↓ 4 callersFunctionkpts_to_patch_idx
(args, img1_kps, num_patches)
C_score/utils/utils_correspondence.py:384
↓ 4 callersFunctionllava_aggregation
(results, category)
llava/eval/lmms-eval/lmms_eval/tasks/llava-in-the-wild/utils.py:178
↓ 4 callersFunctionllava_aggregation
(results, category)
llava/eval/lmms-eval/lmms_eval/tasks/multilingual-llava-bench-in-the-wild/utils.py:178
↓ 4 callersFunctionllava_aggregation
(results, category)
llava/eval/lmms-eval/lmms_eval/tasks/llava-bench-coco/utils.py:181
↓ 4 callersFunctionload_checkpoint_to_model
(checkpoint, model, strict=False)
diffusers/scripts/convert_kandinsky_to_diffusers.py:1320
↓ 4 callersMethodload_module
(name, value)
diffusers/src/diffusers/loaders/single_file.py:480
↓ 4 callersMethodmode
(self)
diffusers/src/diffusers/models/autoencoders/vae.py:819
↓ 4 callersMethodmodel
(self)
llava/eval/lmms-eval/lmms_eval/models/fuyu.py:113
↓ 4 callersFunctionparse_choice_img
(choice: str, img_token: str)
llava/eval/lmms-eval/lmms_eval/tasks/seedbench_2/utils.py:8
↓ 4 callersFunctionparse_list
(value)
diffusers/scripts/convert_if.py:703
↓ 4 callersMethodpartition
Partitions t0 and t1 into n_samples intervals. Args: ts: [batch_size, *shape, n_samples, 1] Return:
diffusers/src/diffusers/pipelines/shap_e/renderer.py:245
↓ 4 callersFunctionpermute_indices
Permutes indices based on the rules provided in the flip_list. Args: - flip_list (list): List containing integers or lists of intege
C_score/utils/utils_geoware.py:151
↓ 4 callersMethodprecondition_inputs
(self, sample, sigma)
diffusers/src/diffusers/schedulers/scheduling_edm_euler.py:148
↓ 4 callersMethodprecondition_outputs
(self, sample, model_output, sigma)
diffusers/src/diffusers/schedulers/scheduling_edm_euler.py:161
↓ 4 callersMethodprepare_control_image
( self, image, width, height, batch_size, num_images_per_promp
diffusers/examples/community/fresco_v2v.py:1915
↓ 4 callersMethodprevious_timestep
(self, timestep)
diffusers/src/diffusers/schedulers/scheduling_lcm.py:645
↓ 4 callersFunctionread_jsonl
(path: str, key: str=None)
llava/eval/generate_webpage_data_from_table.py:10
↓ 4 callersFunctionrearrange_3
(tensor, f)
diffusers/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero_sdxl.py:64
↓ 4 callersFunctionrearrange_3
(tensor, f)
diffusers/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py:38
↓ 4 callersFunctionrearrange_4
(tensor)
diffusers/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero_sdxl.py:70
↓ 4 callersFunctionrearrange_4
(tensor)
diffusers/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py:43
↓ 4 callersFunctionrecurse_remove_peft_layers
r""" Recursively replace all instances of `LoraLayer` with corresponding new layers in `model`.
diffusers/src/diffusers/utils/peft_utils.py:31
↓ 4 callersFunctionrenew_temp_conv_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_i2vgen_to_diffusers.py:101
↓ 4 callersFunctionrenew_temp_conv_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_ms_text_to_video_to_diffusers.py:106
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_original_audioldm2_to_diffusers.py:88
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_svd_to_diffusers.py:556
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_versatile_diffusion_to_diffusers.py:128
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_original_audioldm_to_diffusers.py:79
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_zero123_to_diffusers.py:624
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_original_musicldm_to_diffusers.py:80
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_unidiffuser_to_diffusers.py:48
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:103
↓ 4 callersFunctionrenumber_indices
input: a nested list output: a nested list with all the numbers replaced by the next number in the counter
C_score/utils/utils_geoware.py:137
↓ 4 callersMethodreset_device_map
r""" Resets the device maps (if any) to None.
diffusers/src/diffusers/pipelines/pipeline_utils.py:1168
↓ 4 callersFunctionresnet_to_diffusers_checkpoint
(checkpoint, *, diffusers_resnet_prefix, resnet_prefix)
diffusers/scripts/convert_kandinsky_to_diffusers.py:750
↓ 4 callersFunctionresnet_to_diffusers_checkpoint
(checkpoint, *, diffusers_resnet_prefix, resnet_prefix)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:799
↓ 4 callersFunctionretrieve_latents
( encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample" )
diffusers/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py:108
↓ 4 callersFunctionretrieve_latents
( encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample" )
diffusers/examples/community/pipeline_sdxl_style_aligned.py:377
↓ 4 callersFunctionretrieve_latents
( encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample" )
diffusers/examples/community/lpw_stable_diffusion_xl.py:489
↓ 4 callersFunctionrunEngine
(engine, feed_dict, stream)
diffusers/examples/community/stable_diffusion_tensorrt_txt2img.py:396
↓ 4 callersMethodsample
(self, generator: Optional[torch.Generator] = None)
diffusers/src/diffusers/models/autoencoders/vae.py:780
↓ 4 callersFunctionset_adapter_layers
(model, enabled=True)
diffusers/src/diffusers/utils/peft_utils.py:204
↓ 4 callersMethodset_attn_processor
r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o
diffusers/src/diffusers/models/unets/unet_2d_condition.py:720
↓ 4 callersMethodset_joint_mode
r"""Manually set the generation mode to unconditional joint image-text generation.
diffusers/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py:264
↓ 4 callersMethodset_lora_device
Moves the LoRAs listed in `adapter_names` to a target device. Useful for offloading the LoRA to the CPU in case you want to load mult
diffusers/src/diffusers/loaders/lora.py:1128
↓ 4 callersMethodset_progress_bar_config
(self, **kwargs)
diffusers/src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_combined.py:198
↓ 4 callersMethodset_progress_bar_config
(self, **kwargs)
diffusers/src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py:211
↓ 4 callersFunctionset_verbosity
Set the verbosity level for the 🤗 Diffusers' root logger. Args: verbosity (`int`): Logging level which can be one of:
diffusers/src/diffusers/utils/logging.py:147
↓ 4 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_ldm_original_checkpoint_to_diffusers.py:25
↓ 4 callersFunctionswap_scale_shift
(weight, dim)
diffusers/src/diffusers/loaders/single_file_utils.py:1606
↓ 4 callersFunctiontext2Markdown
(text)
llava/eval/webpage/script.js:35
↓ 4 callersMethodto
(self, torch_device: Optional[Union[str, torch.device]] = None, silence_dtype_warnings: bool = False)
diffusers/examples/community/stable_diffusion_tensorrt_txt2img.py:718
↓ 4 callersFunctiontokenize_prompt
(tokenizer, prompt)
diffusers/examples/amused/train_amused.py:402
↓ 4 callersFunctiontokenize_prompt
(tokenizer, prompt, add_special_tokens=False)
diffusers/examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py:1000
↓ 4 callersFunctiontranslate_prompt
helper function to translate prompt to English
diffusers/examples/community/multilingual_stable_diffusion.py:41
↓ 4 callersMethodunfuse_qkv_projections
Disables the fused QKV projection if enabled. <Tip warning={true}> This API is 🧪 experimental. </Tip>
diffusers/src/diffusers/models/unets/unet_i2vgen_xl.py:502
↓ 4 callersFunctionupdate_mapping_from_spec
(device_fn_dict: Dict[str, Callable], attribute_name: str)
diffusers/src/diffusers/utils/testing_utils.py:992
↓ 4 callersFunctionupdate_vae_resnet_ldm_to_diffusers
(keys, new_checkpoint, checkpoint, mapping)
diffusers/src/diffusers/loaders/single_file_utils.py:759
↓ 4 callersFunctionvqvae_attention_to_diffusers_checkpoint
(checkpoint, *, diffusers_attention_prefix, attention_prefix)
diffusers/scripts/convert_vq_diffusion_to_diffusers.py:433
← previousnext →801–900 of 12,826, ranked by callers