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
↓ 3 callersFunctionrandom_mask
(im_shape, ratio=1, mask_full_image=False)
diffusers/examples/research_projects/dreambooth_inpaint/train_dreambooth_inpaint_lora.py:54
↓ 3 callersFunctionrandom_mask
(im_shape, ratio=1, mask_full_image=False)
diffusers/examples/research_projects/dreambooth_inpaint/train_dreambooth_inpaint.py:58
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_original_audioldm2_to_diffusers.py:105
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_svd_to_diffusers.py:186
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_versatile_diffusion_to_diffusers.py:144
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_ldm_original_checkpoint_to_diffusers.py:57
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_original_audioldm_to_diffusers.py:96
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_zero123_to_diffusers.py:230
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/scripts/convert_original_musicldm_to_diffusers.py:97
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
diffusers/examples/research_projects/promptdiffusion/convert_original_promptdiffusion_to_diffusers.py:119
↓ 3 callersFunctionrescale_noise_cfg
Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and Sample Steps are Flawed](http
diffusers/examples/community/pipeline_demofusion_sdxl.py:82
↓ 3 callersMethodreset_x0
(self, x_in, cond, act_dim)
diffusers/src/diffusers/experimental/rl/value_guided_sampling.py:84
↓ 3 callersMethodreshape_heads_to_batch_dim
(self, tensor)
diffusers/src/diffusers/models/attention_flax.py:165
↓ 3 callersFunctionreshape_tensor
(x, heads)
diffusers/examples/community/pipeline_stable_diffusion_xl_instandid_img2img.py:65
↓ 3 callersFunctionreshape_tensor
(x, heads)
diffusers/examples/community/pipeline_stable_diffusion_xl_instantid.py:65
↓ 3 callersFunctionresize
(images: PIL.Image.Image, img_size: int)
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py:39
↓ 3 callersFunctionretrieve_latents
( encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample" )
diffusers/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py:77
↓ 3 callersMethodsave_pretrained
Save a model and its configuration file to a directory, so that it can be re-loaded using the `[`~models.adapter.MultiAdapter.from_pr
diffusers/src/diffusers/models/adapter.py:103
↓ 3 callersMethodset_adapter
Sets a specific adapter by forcing the model to only use that adapter and disables the other adapters. If you are not familiar with
diffusers/src/diffusers/loaders/peft.py:74
↓ 3 callersFunctionset_attention_weights
(new_layer, old_checkpoint, index)
diffusers/scripts/convert_ncsnpp_original_checkpoint_to_diffusers.py:48
↓ 3 callersMethodset_attn_processor
r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o
diffusers/src/diffusers/pipelines/deprecated/versatile_diffusion/modeling_text_unet.py:852
↓ 3 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_motion_model.py:653
↓ 3 callersMethodset_image
(self, img, switch)
diffusers/examples/research_projects/multi_subject_dreambooth_inpainting/train_multi_subject_dreambooth_inpainting.py:241
↓ 3 callersFunctionset_image_size
(checkpoint, image_size=None)
diffusers/src/diffusers/loaders/single_file_utils.py:501
↓ 3 callersFunctionset_seed
(seed=42)
C_score/preprocess_map.py:11
↓ 3 callersMethodset_sigmas
Sets the noise scales used for the diffusion chain (to be run before inference). The sigmas control the weight of the `drift` and `di
diffusers/src/diffusers/schedulers/scheduling_sde_ve.py:125
↓ 3 callersMethodset_use_memory_efficient_attention_xformers
( self, valid: bool, attention_op: Optional[Callable] = None )
diffusers/src/diffusers/pipelines/pipeline_utils.py:1683
↓ 3 callersMethodset_use_memory_efficient_attention_xformers
( self, valid: bool, attention_op: Optional[Callable] = None )
diffusers/src/diffusers/models/modeling_utils.py:207
↓ 3 callersMethodset_use_npu_flash_attention
r""" Set the switch for the npu flash attention.
diffusers/src/diffusers/models/modeling_utils.py:177
↓ 3 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_i2vgen_to_diffusers.py:91
↓ 3 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
diffusers/scripts/convert_ms_text_to_video_to_diffusers.py:96
↓ 3 callersFunctionslerp
(t, v0, v1, DOT_THRESHOLD=0.9995)
diffusers/examples/community/clip_guided_images_mixing_stable_diffusion.py:44
↓ 3 callersFunctionsort_objects
Sort a list of objects following the rules of isort (all uppercased first, camel-cased second and lower-cased last). Args: objec
diffusers/utils/custom_init_isort.py:143
↓ 3 callersFunctionsplit_attentions
(*, weight, bias, split, chunk_size)
diffusers/scripts/convert_kandinsky_to_diffusers.py:838
↓ 3 callersFunctionsplit_attentions
(*, weight, bias, split, chunk_size)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:887
↓ 3 callersFunctionstate_dicts_almost_equal
(sd1, sd2)
diffusers/tests/lora/utils.py:46
↓ 3 callersMethodtearDown
(self)
diffusers/tests/models/autoencoders/test_models_vae.py:564
↓ 3 callersMethodto_torch
(self, x_in)
diffusers/src/diffusers/experimental/rl/value_guided_sampling.py:77
↓ 3 callersFunctiontokenize_prompt
(tokenizer, prompt, tokenizer_max_length=None)
diffusers/examples/dreambooth/train_dreambooth.py:771
↓ 3 callersFunctiontokenize_prompt
(tokenizer, prompt, tokenizer_max_length=None)
diffusers/examples/dreambooth/train_dreambooth_lora.py:699
↓ 3 callersFunctiontokenize_prompt
(tokenizer, prompt)
diffusers/examples/text_to_image/train_text_to_image_lora_sdxl.py:505
↓ 3 callersFunctiontokenize_prompt
(tokenizer, prompt, tokenizer_max_length=None)
diffusers/examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth.py:791
↓ 3 callersFunctiontokenize_prompt
(tokenizer, prompt, tokenizer_max_length=None)
diffusers/examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth_lora.py:719
↓ 3 callersFunctiontokenize_prompt
(tokenizer, prompt)
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_lora_sdxl.py:475
↓ 3 callersMethodtranspose_for_scores
(self, projection)
diffusers/src/diffusers/models/vae_flax.py:232
↓ 3 callersMethodtranspose_for_scores
(self, projection: torch.Tensor)
diffusers/src/diffusers/models/unets/unet_1d_blocks.py:332
↓ 3 callersFunctionunet_conv_in
(checkpoint, original_unet_prefix)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:584
↓ 3 callersFunctionunet_conv_norm_out
(checkpoint, original_unet_prefix)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:598
↓ 3 callersFunctionunet_conv_out
(checkpoint, original_unet_prefix)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:612
↓ 3 callersFunctionunet_downblock_to_diffusers_checkpoint
( model, checkpoint, *, diffusers_down_block_idx, original_down_block_idx, original_unet_prefix, num_head_
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:626
↓ 3 callersFunctionunet_midblock_to_diffusers_checkpoint
(model, checkpoint, *, original_unet_prefix, num_head_channels)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:685
↓ 3 callersFunctionunet_time_embeddings
(checkpoint, original_unet_prefix)
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:568
↓ 3 callersFunctionunet_upblock_to_diffusers_checkpoint
( model, checkpoint, *, diffusers_up_block_idx, original_up_block_idx, original_unet_prefix, num_head_chan
diffusers/scripts/convert_kakao_brain_unclip_to_diffusers.py:729
↓ 3 callersFunctionunwrap_model
(model)
diffusers/examples/dreambooth/train_dreambooth_lora_sd3.py:1155
↓ 3 callersFunctionunwrap_model
(model)
diffusers/examples/text_to_image/train_text_to_image_lora.py:667
↓ 3 callersFunctionunwrap_model
(model)
diffusers/examples/t2i_adapter/train_t2i_adapter_sdxl.py:946
↓ 3 callersFunctionunwrap_model
(model)
diffusers/examples/controlnet/train_controlnet.py:821
↓ 3 callersFunctionunwrap_model
(model)
diffusers/examples/controlnet/train_controlnet_sdxl.py:902
↓ 3 callersFunctionunwrap_model
(model)
diffusers/examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_lora.py:668
↓ 3 callersFunctionunwrap_model
(model)
diffusers/examples/research_projects/gligen/train_gligen_text.py:335
↓ 3 callersMethodupcast_vae
(self)
diffusers/src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion_xl.py:694
↓ 3 callersFunctionupdateQuestionSelect
(question_id)
llava/eval/webpage/script.js:48
↓ 3 callersFunctionvalue_function
()
diffusers/scripts/convert_models_diffuser_to_diffusers.py:59
↓ 2 callersFunctionFeedForward
(dim, mult=4)
llava/model/multimodal_projector/perceiver_helpers.py:15
↓ 2 callersMethod__init__
(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None)
llava/model/language_model/mpt/norm.py:35
↓ 2 callersMethod__init__
pass a string `regex` to run `re.compile(r"regex")` on. `fallback` defines the output returned if no matches for the regex are locate
llava/eval/lmms-eval/lmms_eval/filters/extraction.py:32
↓ 2 callersMethod__init__
(self)
llava/train/train.py:55
↓ 2 callersMethod__init__
(self, config: CLIPTextConfig)
diffusers/src/diffusers/pipelines/blip_diffusion/modeling_ctx_clip.py:47
↓ 2 callersMethod__init__
( self, unet: UNet2DConditionModel, scheduler: DDPMScheduler, movq: VQModel,
diffusers/src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_combined.py:140
↓ 2 callersMethod__init__
( self, text_encoder: MultilingualCLIP, tokenizer: XLMRobertaTokenizer, unet:
diffusers/src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py:148
↓ 2 callersMethod__init__
( self, dim: int, num_attention_heads: int, cross_attention_dim: int = 1024,
diffusers/src/diffusers/models/transformers/hunyuan_transformer_2d.py:100
↓ 2 callersMethod__init__
( self, in_channels: int, layers_per_block: int = 2, num_attention_heads: int
diffusers/src/diffusers/models/unets/unet_motion_model.py:56
↓ 2 callersMethod__init__
(self, onnx_graph, verbose=False)
diffusers/scripts/convert_stable_diffusion_controlnet_to_onnx.py:27
↓ 2 callersMethod__init__
(self)
diffusers/examples/community/rerender_a_video.py:170
↓ 2 callersMethod__init__
(self, in_planes, planes, stride=1)
C_score/model_utils/projection_network.py:139
↓ 2 callersMethod__init__additional__
(self)
diffusers/examples/community/lpw_stable_diffusion_onnx.py:489
↓ 2 callersMethod__post_init__
(self)
diffusers/examples/community/mixture_canvas.py:48
↓ 2 callersMethod_adapt_language
(self, prompt_embeds: torch.Tensor)
diffusers/examples/community/gluegen.py:245
↓ 2 callersMethod_best_guess_weight_name
( cls, pretrained_model_name_or_path_or_dict, file_extension=".safetensors", local_files_only=False
diffusers/src/diffusers/loaders/lora.py:295
↓ 2 callersFunction_bwd_kernel_one_col_block
(start_n, Q, K, V, Bias, DO, DQ, DK, DV, LSE, D, softmax_scale, stride_qm, stride_kn, stride_vn, stride_bm, st
llava/model/language_model/mpt/flash_attn_triton.py:184
↓ 2 callersFunction_bwd_store_dk_dv
(dk_ptrs, dv_ptrs, dk, dv, offs_n, offs_d, seqlen_k, headdim, EVEN_M: tl.constexpr, EVEN_N: tl.constexpr, EVEN
llava/model/language_model/mpt/flash_attn_triton.py:168
↓ 2 callersFunction_center_crop_wide
( image: Union[torch.Tensor, List[torch.Tensor], PIL.Image.Image, List[PIL.Image.Image]], resolution: Tupl
diffusers/src/diffusers/pipelines/i2vgen_xl/pipeline_i2vgen_xl.py:762
↓ 2 callersFunction_center_text
(text, width)
diffusers/utils/check_table.py:81
↓ 2 callersFunction_check_if_shards_exist_locally
(local_dir, subfolder, original_shard_filenames)
diffusers/src/diffusers/utils/hub_utils.py:404
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/pixart_alpha/pipeline_pixart_sigma.py:472
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/pixart_alpha/pipeline_pixart_alpha.py:545
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img_superresolution.py:220
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if.py:424
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py:178
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py:468
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py:222
↓ 2 callersMethod_clean_caption
(self, caption)
diffusers/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting.py:508
↓ 2 callersFunction_compare_versions
(op, got_ver, want_ver, requirement, pkg, hint)
diffusers/src/diffusers/utils/versions.py:37
↓ 2 callersMethod_compute_exponential_sigmas
Implementation closely follows k-diffusion. https://github.com/crowsonkb/k-diffusion/blob/6ab5146d4a5ef63901326489f31f1d8e7dd36b48/k_diffusio
diffusers/src/diffusers/schedulers/scheduling_edm_euler.py:238
↓ 2 callersMethod_compute_exponential_sigmas
Implementation closely follows k-diffusion. https://github.com/crowsonkb/k-diffusion/blob/6ab5146d4a5ef63901326489f31f1d8e7dd36b48/k_diffusio
diffusers/src/diffusers/schedulers/scheduling_edm_dpmsolver_multistep.py:289
↓ 2 callersMethod_compute_karras_sigmas
Constructs the noise schedule of Karras et al. (2022).
diffusers/src/diffusers/schedulers/scheduling_edm_euler.py:227
↓ 2 callersMethod_compute_karras_sigmas
Constructs the noise schedule of Karras et al. (2022).
diffusers/src/diffusers/schedulers/scheduling_edm_dpmsolver_multistep.py:277
↓ 2 callersMethod_convert_deprecated_attention_blocks
(self, state_dict: OrderedDict)
diffusers/src/diffusers/models/modeling_utils.py:1068
↓ 2 callersFunction_convert_pt_to_pil
(image: Union[torch.Tensor, List[torch.Tensor]])
diffusers/src/diffusers/pipelines/i2vgen_xl/pipeline_i2vgen_xl.py:734
↓ 2 callersMethod_convert_to_karras
Constructs the noise schedule of Karras et al. (2022).
diffusers/src/diffusers/schedulers/scheduling_consistency_models.py:248
← previousnext →1,101–1,200 of 12,826, ranked by callers