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
↓ 6 callersMethod_compare_component_configs
(self, pipe, single_file_pipe)
diffusers/tests/single_file/single_file_testing_utils.py:206
↓ 6 callersFunction_copy_linear
(hf_linear, pt_linear)
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:752
↓ 6 callersFunction_copy_linear
(hf_linear, pt_linear)
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:820
↓ 6 callersMethod_get_add_time_ids
(self, original_size, crops_coords_top_left, target_size, dtype)
diffusers/examples/community/pipeline_demofusion_sdxl.py:501
↓ 6 callersMethod_test_save_load_local
(self)
diffusers/tests/pipelines/deepfloyd_if/__init__.py:251
↓ 6 callersMethod_upload_folder
Uploads all files in `working_dir` to `repo_id`.
diffusers/src/diffusers/utils/hub_utils.py:507
↓ 6 callersMethodadd_partial
(self, attr, req, res)
llava/eval/lmms-eval/lmms_eval/api/model.py:126
↓ 6 callersMethodapply
Defines the operation to perform on a list of the `inst.resps` properties of `Instance` objects. Should return the list of (filtered)
llava/eval/lmms-eval/lmms_eval/api/filter.py:22
↓ 6 callersFunctionassign_attention_to_checkpoint
(new_checkpoint, unet_state_dict, old_path, new_path, config)
diffusers/scripts/convert_if.py:601
↓ 6 callersFunctionassign_to_checkpoint
This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take
diffusers/scripts/convert_unidiffuser_to_diffusers.py:110
↓ 6 callersFunctionbroadcast_to_shape_from_left
(x: jnp.ndarray, shape: Tuple[int])
diffusers/src/diffusers/schedulers/scheduling_utils_flax.py:191
↓ 6 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:223
↓ 6 callersFunctioncreate_ip_adapter_state_dict
(model)
diffusers/tests/models/unets/test_models_unet_2d_condition.py:89
↓ 6 callersFunctiondeps_list
(*pkgs)
diffusers/setup.py:165
↓ 6 callersMethoddevice
(self)
diffusers/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py:873
↓ 6 callersFunctiondevice_view
(t)
diffusers/examples/community/stable_diffusion_tensorrt_txt2img.py:89
↓ 6 callersMethoddisable_slicing
r""" Disable sliced VAE decoding. If `enable_slicing` was previously enabled, this method will go back to computing decoding in one st
diffusers/src/diffusers/models/autoencoders/autoencoder_kl.py:158
↓ 6 callersMethodenable_freeu
r"""Enables the FreeU mechanism from https://arxiv.org/abs/2309.11497. The suffixes after the scaling factors represent the stage blocks wher
diffusers/src/diffusers/models/unets/unet_i2vgen_xl.py:444
↓ 6 callersMethodenable_model_cpu_offload
r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti
diffusers/src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_combined.py:410
↓ 6 callersMethodenable_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/models/autoencoders/autoencoder_kl.py:151
↓ 6 callersFunctionexists
(val)
llava/model/multimodal_projector/perceiver_helpers.py:11
↓ 6 callersFunctionflush
Wipes off memory.
diffusers/benchmarks/utils.py:40
↓ 6 callersMethodget_dummy_components
(self, time_cond_proj_dim=None)
diffusers/tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_adapter.py:426
↓ 6 callersMethodget_dummy_components
(self)
diffusers/tests/pipelines/stable_diffusion/test_stable_diffusion_instruction_pix2pix.py:70
↓ 6 callersMethodget_dummy_components
(self)
diffusers/tests/pipelines/pixart_alpha/test_pixart.py:54
↓ 6 callersMethodget_dummy_components
(self, time_cond_proj_dim=None)
diffusers/tests/pipelines/animatediff/test_animatediff_sdxl.py:57
↓ 6 callersMethodget_dummy_inputs
(self, device, seed=0)
diffusers/tests/pipelines/stable_diffusion_3/test_pipeline_stable_diffusion_3_img2img.py:109
↓ 6 callersMethodget_dummy_inputs
(self, device, seed=0, height=64, width=64)
diffusers/tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_adapter.py:432
↓ 6 callersMethodget_dummy_inputs
(self, device, seed=0, height=64, width=64, num_images=1)
diffusers/tests/pipelines/stable_diffusion_adapter/test_stable_diffusion_adapter.py:231
↓ 6 callersMethodget_dummy_inputs
(self, device, seed=0)
diffusers/tests/pipelines/stable_diffusion_2/test_stable_diffusion.py:142
↓ 6 callersMethodget_dummy_inputs
(self, device, seed=0)
diffusers/tests/pipelines/animatediff/test_animatediff_sdxl.py:135
↓ 6 callersMethodget_generator
(self, seed)
diffusers/tests/pipelines/test_pipelines_common.py:872
↓ 6 callersMethodget_inputs
(self, device, generator_device="cpu", dtype=torch.float32, seed=0)
diffusers/tests/pipelines/stable_diffusion_2/test_stable_diffusion.py:544
↓ 6 callersMethodget_inputs
(self, seed=0)
diffusers/tests/pipelines/stable_diffusion/test_stable_diffusion_instruction_pix2pix.py:284
↓ 6 callersMethodget_models
(self, decay=0.9999)
diffusers/tests/others/test_ema.py:38
↓ 6 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_edm_dpmsolver_multistep.py:17
↓ 6 callersMethodget_scheduler_config
(self, **kwargs)
diffusers/tests/schedulers/test_scheduler_euler.py:13
↓ 6 callersMethodinvert
( self, image_path: str, prompt: str, num_inner_steps=10, early_stop_epsilon=1e-6, num_inference_steps
diffusers/examples/community/pipeline_null_text_inversion.py:178
↓ 6 callersFunctionis_k_diffusion_available
()
diffusers/src/diffusers/utils/import_utils.py:390
↓ 6 callersFunctionlistinstr
(lst, s)
llava/eval/lmms-eval/lmms_eval/models/xcomposer2_4KHD.py:275
↓ 6 callersMethodload_model
(self)
llava/model/multimodal_encoder/clip_encoder.py:22
↓ 6 callersMethodprepare_image
r""" Prepares the input image for processing. Args: image (torch.Tensor or PIL.Image.Image or list): The input image(s).
diffusers/examples/community/stable_diffusion_reference.py:663
↓ 6 callersMethodprepare_init_args_and_inputs_for_common
(self)
diffusers/tests/models/unets/test_unet_2d_blocks.py:155
↓ 6 callersMethodprepare_init_args_and_inputs_for_common
(self)
diffusers/tests/models/unets/test_models_unet_spatiotemporal.py:87
↓ 6 callersFunctionprocess_images
(images, image_processor, model_cfg)
llava/mm_utils.py:78
↓ 6 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:117
↓ 6 callersFunctionrenew_attention_paths
(old_list, n_shave_prefix_segments=0, in_mid=False)
diffusers/scripts/convert_ddpm_original_checkpoint_to_diffusers.py:35
↓ 6 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_if.py:571
↓ 6 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_i2vgen_to_diffusers.py:112
↓ 6 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_ldm_original_checkpoint_to_diffusers.py:35
↓ 6 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_original_audioldm_to_diffusers.py:56
↓ 6 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_zero123_to_diffusers.py:208
↓ 6 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_original_musicldm_to_diffusers.py:57
↓ 6 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/scripts/convert_ms_text_to_video_to_diffusers.py:117
↓ 6 callersFunctionrenew_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:81
↓ 6 callersFunctionrenew_vae_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:138
↓ 6 callersMethodreset
(self)
diffusers/examples/vqgan/train_vqgan.py:64
↓ 6 callersFunctionresolve_interpolation_mode
Maps a string describing an interpolation function to the corresponding torchvision `InterpolationMode` enum. The full list of supported enum
diffusers/src/diffusers/training_utils.py:78
↓ 6 callersFunctionsave_image
(image, name)
diffusers/scripts/convert_consistency_decoder.py:181
↓ 6 callersFunctionset_requires_grad
(model, value)
diffusers/examples/community/clip_guided_images_mixing_stable_diffusion.py:75
↓ 6 callersFunctionset_requires_grad
(model, value)
diffusers/examples/community/clip_guided_stable_diffusion_img2img.py:123
↓ 6 callersFunctionset_requires_grad
(model, value)
diffusers/examples/community/clip_guided_stable_diffusion.py:49
↓ 6 callersFunctionset_resnet_weights
(new_layer, old_checkpoint, index)
diffusers/scripts/convert_ncsnpp_original_checkpoint_to_diffusers.py:63
↓ 6 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_if.py:539
↓ 6 callersMethodto
(self, torch_device: Optional[Union[str, torch.device]] = None, silence_dtype_warnings: bool = False)
diffusers/examples/community/stable_diffusion_tensorrt_inpaint.py:806
↓ 6 callersMethodto
(self, torch_device: Optional[Union[str, torch.device]] = None, silence_dtype_warnings: bool = False)
diffusers/examples/community/stable_diffusion_tensorrt_img2img.py:806
↓ 6 callersFunctiontokenize_prompt
(tokenizer, prompt)
diffusers/examples/dreambooth/train_dreambooth_lora_sd3.py:837
↓ 6 callersFunctionunwrap_model
(model)
diffusers/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py:1493
↓ 6 callersFunctionunwrap_model
(model)
diffusers/examples/instruct_pix2pix/train_instruct_pix2pix.py:543
↓ 6 callersFunctionupfirdn2d_native
( tensor: torch.Tensor, kernel: torch.Tensor, up: int = 1, down: int = 1, pad: Tuple[int,
diffusers/src/diffusers/models/upsampling.py:351
↓ 5 callersMethod__init__
(self, config: LDMBertConfig)
diffusers/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py:720
↓ 5 callersMethod__init__
(self, dim: int)
diffusers/src/diffusers/pipelines/unidiffuser/modeling_uvit.py:123
↓ 5 callersMethod__init__
( self, dim: int, dim_out: Optional[int] = None, mult: int = 4, dropou
diffusers/src/diffusers/models/attention.py:746
↓ 5 callersMethod__init__
(self, model, device, max_batch_size, embedding_dim)
diffusers/examples/community/stable_diffusion_tensorrt_inpaint.py:553
↓ 5 callersMethod__init__
(self, model, device, max_batch_size, embedding_dim)
diffusers/examples/community/stable_diffusion_tensorrt_img2img.py:553
↓ 5 callersFunction_cast_if_autocast_enabled
(tensor)
llava/model/language_model/mpt/norm.py:3
↓ 5 callersFunction_chunked_feed_forward
(ff: nn.Module, hidden_states: torch.Tensor, chunk_dim: int, chunk_size: int)
diffusers/src/diffusers/models/attention.py:31
↓ 5 callersMethod_encode_vae_image
(self, image: torch.Tensor, generator: torch.Generator)
diffusers/examples/community/pipeline_sdxl_style_aligned.py:1109
↓ 5 callersFunction_extract_into_tensor
(arr, timesteps, broadcast_shape)
diffusers/scripts/convert_consistency_decoder.py:26
↓ 5 callersFunction_get_pipeline_class
( class_obj, config=None, load_connected_pipeline=False, custom_pipeline=None, repo_id=Non
diffusers/src/diffusers/pipelines/pipeline_loading_utils.py:335
↓ 5 callersMethod_init_step_index
(self, timestep)
diffusers/src/diffusers/schedulers/scheduling_lcm.py:269
↓ 5 callersFunction_print_list
Pretty print a list of elements with one line per element and a - starting each line.
diffusers/utils/tests_fetcher.py:828
↓ 5 callersFunction_tile2latent_indices
Given a tile row and column numbers returns the range of latents affected by that tiles in the overall image Returns a tuple with: - Star
diffusers/examples/community/mixture_tiling.py:72
↓ 5 callersMethodadd_noise
( self, original_samples: torch.Tensor, noise: torch.Tensor, timesteps: torch.
diffusers/src/diffusers/schedulers/scheduling_ddpm.py:499
↓ 5 callersMethodapply_overlay
overlay the inpaint output to the original image
diffusers/src/diffusers/image_processor.py:651
↓ 5 callersMethodapply_watermark
(self, images: torch.Tensor)
diffusers/src/diffusers/pipelines/stable_diffusion_xl/watermark.py:24
↓ 5 callersFunctionbuild_vision_projector
(config, delay_load=False, **kwargs)
llava/model/multimodal_projector/builder.py:34
↓ 5 callersMethodcheck_copy_consistency
(self, comment, class_name, class_code, overwrite_result=None)
diffusers/tests/others/test_check_copies.py:62
↓ 5 callersMethodcheck_over_configs
(self, time_step=0, **config)
diffusers/tests/schedulers/test_scheduler_pndm.py:25
↓ 5 callersFunctioncheck_peft_version
r""" Checks if the version of PEFT is compatible. Args: version (`str`): The version of PEFT to check against.
diffusers/src/diffusers/utils/peft_utils.py:278
↓ 5 callersFunctioncompare_versions
Args: Compares a library version to some requirement using a given operation. library_or_version (`str` or `packaging.version.Version
diffusers/src/diffusers/utils/import_utils.py:647
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
llava/eval/lmms-eval/lmms_eval/tasks/refcoco+/utils_rec.py:129
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
llava/eval/lmms-eval/lmms_eval/tasks/refcoco/utils_rec.py:129
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
llava/eval/lmms-eval/lmms_eval/tasks/screenspot/utils_rec.py:93
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
llava/eval/lmms-eval/lmms_eval/tasks/refcocog/utils_rec.py:129
↓ 5 callersFunctionconvert_all_state_dict_to_peft
r""" Attempts to first `convert_state_dict_to_peft`, and if it doesn't detect `lora_linear_layer` for a valid `DIFFUSERS` LoRA for example, at
diffusers/src/diffusers/utils/state_dict_utils.py:256
↓ 5 callersFunctionconvert_state_dict_to_kohya
r""" Converts a `PEFT` state dict to `Kohya` format that can be used in AUTOMATIC1111, ComfyUI, SD.Next, InvokeAI, etc. The method only suppor
diffusers/src/diffusers/utils/state_dict_utils.py:275
↓ 5 callersMethoddecode
(self, latents, deterministic: bool = True, return_dict: bool = True)
diffusers/src/diffusers/models/vae_flax.py:849
↓ 5 callersMethoddisable_tiling
r""" Disable tiled VAE decoding. If `enable_tiling` was previously enabled, this method will go back to computing decoding in one step
diffusers/src/diffusers/models/autoencoders/autoencoder_kl.py:144
↓ 5 callersMethoddoc_to_text
(self, doc)
llava/eval/lmms-eval/lmms_eval/api/task.py:345
← previousnext →501–600 of 12,826, ranked by callers