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 callersFunctioncompute_density_for_timestep_sampling
Compute the density for sampling the timesteps when doing SD3 training. Courtesy: This was contributed by Rafie Walker in https://github.com/hugg
diffusers/src/diffusers/training_utils.py:224
↓ 2 callersMethodcompute_loss
(self, predictions, targets)
diffusers/src/diffusers/pipelines/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_pix2pix_zero.py:224
↓ 2 callersFunctioncompute_loss_weighting_for_sd3
Computes loss weighting scheme for SD3 training. Courtesy: This was contributed by Rafie Walker in https://github.com/huggingface/diffusers/pull/
diffusers/src/diffusers/training_utils.py:245
↓ 2 callersFunctioncompute_pck
(args, save_path, aggre_net, files, kps, category=None, used_points=None, thresholds=None)
C_score/pck_train_two.py:66
↓ 2 callersFunctioncompute_pck
(args, save_path, aggre_net, files, kps, category=None, used_points=None, thresholds=None)
C_score/pck_train.py:57
↓ 2 callersFunctionconditional_loss
( model_pred: torch.Tensor, target: torch.Tensor, reduction: str = "mean", loss_type: str = "l
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_lora.py:414
↓ 2 callersFunctionconditional_loss
( model_pred: torch.Tensor, target: torch.Tensor, reduction: str = "mean", loss_type: str = "l
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_lora_sdxl.py:516
↓ 2 callersFunctionconditional_loss
( model_pred: torch.Tensor, target: torch.Tensor, reduction: str = "mean", loss_type: str = "l
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image.py:518
↓ 2 callersFunctionconditional_loss
( model_pred: torch.Tensor, target: torch.Tensor, reduction: str = "mean", loss_type: str = "l
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_sdxl.py:603
↓ 2 callersFunctionconstruct_prompt
(sample)
llava/eval/lmms-eval/lmms_eval/tasks/cmmmu/utils.py:24
↓ 2 callersFunctionconstruct_prompt
(doc)
llava/eval/lmms-eval/lmms_eval/tasks/mmmu/utils.py:33
↓ 2 callersFunctionconstruct_prompt
(doc)
llava/eval/lmms-eval/lmms_eval/tasks/mmmu/utils_group_img.py:152
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
C_score/model_utils/projection_network.py:133
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/scripts/convert_original_audioldm2_to_diffusers.py:202
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/scripts/convert_svd_to_diffusers.py:544
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/scripts/convert_versatile_diffusion_to_diffusers.py:247
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/scripts/convert_original_audioldm_to_diffusers.py:201
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/scripts/convert_zero123_to_diffusers.py:670
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/scripts/convert_original_musicldm_to_diffusers.py:200
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/scripts/convert_unidiffuser_to_diffusers.py:96
↓ 2 callersFunctionconv_attn_to_linear
(checkpoint)
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:225
↓ 2 callersFunctionconvert_all_results
(result)
C_score/utils/eval_spair.py:123
↓ 2 callersFunctionconvert_controlnet_checkpoint
( checkpoint, original_config, checkpoint_path, image_size, upcast_attention, extract_
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:1088
↓ 2 callersFunctionconvert_controlnet_checkpoint
( checkpoint, original_config, checkpoint_path, image_size, upcast_attention, extract_
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:1156
↓ 2 callersFunctionconvert_ldm_clip_checkpoint
(checkpoint, local_files_only=False, text_encoder=None)
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:793
↓ 2 callersFunctionconvert_ldm_clip_checkpoint
(checkpoint, local_files_only=False, text_encoder=None)
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:861
↓ 2 callersFunctionconvert_ldm_unet_checkpoint
Takes a state dict and a config, and returns a converted checkpoint.
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:388
↓ 2 callersFunctionconvert_open_clip_checkpoint
( checkpoint, config_name, prefix="cond_stage_model.model.", has_projection=False, local_f
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:924
↓ 2 callersFunctionconvert_open_clip_checkpoint
( checkpoint, config_name, prefix="cond_stage_model.model.", has_projection=False, local_f
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:992
↓ 2 callersFunctionconvert_super_res_pipeline
(tokenizer, text_encoder, feature_extractor, safety_checker, args, stage)
diffusers/scripts/convert_if.py:97
↓ 2 callersFunctionconvert_to_binary_mask
(img_path, threshold=127, angle=None)
C_score/utils/utils_correspondence.py:6
↓ 2 callersFunctionconvert_to_np
(image, resolution)
diffusers/examples/instruct_pix2pix/train_instruct_pix2pix_sdxl.py:473
↓ 2 callersFunctionconvert_to_np
(image, resolution)
diffusers/examples/instruct_pix2pix/train_instruct_pix2pix.py:415
↓ 2 callersFunctionconvert_to_np
(image, resolution)
diffusers/examples/research_projects/instructpix2pix_lora/train_instruct_pix2pix_lora.py:375
↓ 2 callersFunctionconvert_vd_unet_checkpoint
Takes a state dict and a config, and returns a converted checkpoint.
diffusers/scripts/convert_versatile_diffusion_to_diffusers.py:369
↓ 2 callersFunctioncount_letters
(string)
llava/eval/lmms-eval/lmms_eval/tasks/cmmmu/utils.py:291
↓ 2 callersMethodcreate
( cls, common: CommonSchedulerState, init_noise_sigma: jnp.ndarray, timesteps: jnp.ndarray, sigmas: jn
diffusers/src/diffusers/schedulers/scheduling_euler_discrete_flax.py:42
↓ 2 callersMethodcreate
( cls, common: CommonSchedulerState, final_alpha_cumprod: jnp.ndarray, init_no
diffusers/src/diffusers/schedulers/scheduling_ddim_flax.py:46
↓ 2 callersMethodcreate
(cls, common: CommonSchedulerState, init_noise_sigma: jnp.ndarray, timesteps: jnp.ndarray)
diffusers/src/diffusers/schedulers/scheduling_ddpm_flax.py:45
↓ 2 callersMethodcreate
( cls, common: CommonSchedulerState, alpha_t: jnp.ndarray, sigma_t: jnp.ndarra
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_multistep_flax.py:53
↓ 2 callersMethodcreate
( cls, common: CommonSchedulerState, init_noise_sigma: jnp.ndarray, timesteps: jnp.ndarray, sigmas: jn
diffusers/src/diffusers/schedulers/scheduling_lms_discrete_flax.py:46
↓ 2 callersFunctioncreate_dummy_files
Create the content of the dummy files.
diffusers/utils/check_dummies.py:115
↓ 2 callersFunctioncreate_dynamic_module
Creates a dynamic module in the cache directory for modules.
diffusers/src/diffusers/utils/dynamic_modules_utils.py:63
↓ 2 callersFunctioncreate_json_map
Creates a map from a list of tests to run to easily split them by category, when running parallelism of slow tests. Args: test_files
diffusers/utils/tests_fetcher.py:867
↓ 2 callersFunctioncreate_reverse_dependency_map
Create the dependency map from module/test filename to the list of modules/tests that depend on it recursively. Returns: `Dict[str,
diffusers/utils/tests_fetcher.py:729
↓ 2 callersFunctioncreate_unet_diffusers_config
Creates a config for the diffusers based on the config of the LDM model.
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:235
↓ 2 callersFunctioncreate_vae_diffusers_config
Creates a config for the diffusers based on the config of the LDM model.
diffusers/src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py:344
↓ 2 callersMethoddecode_latents
(self, latents)
diffusers/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py:498
↓ 2 callersMethoddecode_latents
(self, latents)
diffusers/examples/community/stable_diffusion_controlnet_inpaint.py:431
↓ 2 callersMethoddecode_latents
(self, latents)
diffusers/examples/community/stable_diffusion_ipex.py:463
↓ 2 callersMethoddecode_latents
Decodes a given array of latents into pixel space
diffusers/examples/community/mixture_canvas.py:291
↓ 2 callersMethoddecode_latents
(self, latents)
diffusers/examples/community/stable_diffusion_controlnet_inpaint_img2img.py:416
↓ 2 callersMethoddecode_latents
(self, latents)
diffusers/examples/community/stable_diffusion_controlnet_img2img.py:332
↓ 2 callersMethoddecode_latents
(self, latents)
diffusers/examples/community/lpw_stable_diffusion.py:688
↓ 2 callersMethoddecode_latents
(self, latents)
diffusers/examples/community/pipeline_zero1to3.py:452
↓ 2 callersMethoddecode_text_latents
(self, text_latents, device)
diffusers/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py:763
↓ 2 callersMethoddecode_to_image
( self, latents, device, size: int = 64, ray_batch_size: int = 4096,
diffusers/src/diffusers/pipelines/shap_e/renderer.py:905
↓ 2 callersMethoddecode_to_mesh
( self, latents, device, grid_size: int = 128, query_batch_size: int =
diffusers/src/diffusers/pipelines/shap_e/renderer.py:950
↓ 2 callersFunctiondecoder
(*, args, checkpoint_map_location)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:966
↓ 2 callersMethoddenormalize
Denormalize an image array to [0,1].
diffusers/src/diffusers/image_processor.py:159
↓ 2 callersMethoddevice
(self)
llava/eval/lmms-eval/lmms_eval/models/llava.py:194
↓ 2 callersMethoddevice
(self)
llava/eval/lmms-eval/lmms_eval/models/llava_hf.py:147
↓ 2 callersMethoddevice
(self)
llava/eval/lmms-eval/lmms_eval/models/idefics2.py:138
↓ 2 callersMethoddisable_cfattn
(self)
diffusers/examples/community/fresco_v2v.py:918
↓ 2 callersMethoddisable_freeu
Disables the FreeU mechanism.
diffusers/src/diffusers/models/unets/unet_i2vgen_xl.py:469
↓ 2 callersMethoddisable_lora_for_text_encoder
Disables the LoRA layers for the text encoder. Args: text_encoder (`torch.nn.Module`, *optional*): The t
diffusers/src/diffusers/loaders/lora.py:913
↓ 2 callersFunctiondisplayAnswers
(index)
llava/eval/webpage/script.js:116
↓ 2 callersFunctiondoc_to_text
(doc, model_specific_prompt_kwargs=None)
llava/eval/lmms-eval/lmms_eval/tasks/mmvet/utils.py:206
↓ 2 callersFunctiondraw_correspondences_lines
draw point correspondences on images. :param points1: a list of (y, x) coordinates of image1, corresponding to points2. :param points2: a
C_score/utils/utils_visualization.py:73
↓ 2 callersMethodembed_text
takes in text and turns it into text embeddings
diffusers/examples/community/interpolate_stable_diffusion.py:377
↓ 2 callersMethodenable_attn_hook
(self, enabled=True)
diffusers/examples/community/llm_grounded_diffusion.py:578
↓ 2 callersMethodenable_fuser
(self, enabled=True)
diffusers/src/diffusers/pipelines/stable_diffusion_gligen/pipeline_stable_diffusion_gligen.py:501
↓ 2 callersMethodenable_fuser
(self, enabled=True)
diffusers/examples/community/llm_grounded_diffusion.py:573
↓ 2 callersMethodenable_lora_for_text_encoder
Enables the LoRA layers for the text encoder. Args: text_encoder (`torch.nn.Module`, *optional*): The te
diffusers/src/diffusers/loaders/lora.py:930
↓ 2 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/examples/community/lpw_stable_diffusion_xl.py:657
↓ 2 callersMethodenable_xformers_memory_efficient_attention
(self, attention_op: Optional[Callable] = None)
diffusers/src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_combined.py:179
↓ 2 callersMethodenable_xformers_memory_efficient_attention
(self, attention_op: Optional[Callable] = None)
diffusers/src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py:193
↓ 2 callersFunctionencode_direction
(position, direction=None)
diffusers/src/diffusers/pipelines/shap_e/renderer.py:74
↓ 2 callersMethodencode_image
(self, image, dtype=None, height=None, width=None, resize_mode="default", crops_coords=None)
diffusers/src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion_xl.py:1404
↓ 2 callersMethodencode_image
(self, image, device, num_images_per_prompt, output_hidden_states=None)
diffusers/examples/community/fresco_v2v.py:1598
↓ 2 callersMethodencode_image
(self, image, device, num_images_per_prompt)
diffusers/examples/community/pipeline_stable_diffusion_xl_ipex.py:505
↓ 2 callersMethodencode_images
(self, images)
llava/model/llava_arch.py:260
↓ 2 callersFunctionencode_position
(position)
diffusers/src/diffusers/pipelines/shap_e/renderer.py:70
↓ 2 callersFunctionencode_prompt
(text_encoder, input_ids, attention_mask, text_encoder_use_attention_mask=None)
diffusers/examples/dreambooth/train_dreambooth.py:788
↓ 2 callersFunctionencode_prompt
(text_encoders, tokenizers, prompt, text_input_ids_list=None)
diffusers/examples/dreambooth/train_dreambooth_lora_sdxl.py:935
↓ 2 callersFunctionencode_prompt
( text_encoders, tokenizers, prompt: str, max_sequence_length, device=None, num_images
diffusers/examples/dreambooth/train_dreambooth_sd3.py:911
↓ 2 callersFunctionencode_prompt
(text_encoder, input_ids, attention_mask, text_encoder_use_attention_mask=None)
diffusers/examples/dreambooth/train_dreambooth_lora.py:716
↓ 2 callersFunctionencode_prompt
(text_encoders, tokenizers, prompt, text_input_ids_list=None)
diffusers/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py:1169
↓ 2 callersFunctionencode_prompt
(text_encoders, tokenizers, prompt, text_input_ids_list=None)
diffusers/examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py:1014
↓ 2 callersFunctionencode_prompt
(text_encoder, input_ids, attention_mask, text_encoder_use_attention_mask=None)
diffusers/examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth.py:808
↓ 2 callersFunctionencode_prompt
(text_encoders, tokenizers, prompt, text_input_ids_list=None)
diffusers/examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth_lora_sdxl.py:954
↓ 2 callersFunctionencode_prompt
(text_encoder, input_ids, attention_mask, text_encoder_use_attention_mask=None)
diffusers/examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth_lora.py:736
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py:408
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/stable_diffusion_sag/pipeline_stable_diffusion_sag.py:198
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py:382
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py:143
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth_img2img.py:178
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_k_diffusion.py:183
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py:300
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
diffusers/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py:271
← previousnext →1,401–1,500 of 12,826, ranked by callers