Functions — github.com/LetterLiGo/SafeGen

hub / github.com/LetterLiGo/SafeGen_CCS2024 / functions

Functions7,383 in github.com/LetterLiGo/SafeGen_CCS2024

⨍ Functions 7,383◇ Types & classes 1,211↳ Endpoints 4

↓ 3 callersMethodget_dummy_inputs

(self, device, seed=0)

tests/pipelines/kandinsky/test_kandinsky.py:211

↓ 3 callersMethodget_dummy_inputs

(self, device, seed=0)

tests/pipelines/kandinsky/test_kandinsky_img2img.py:233

↓ 3 callersMethodget_dummy_inputs

(self, device, seed=0)

tests/pipelines/kandinsky/test_kandinsky_combined.py:171

↓ 3 callersMethodget_dummy_inputs

(self, device, seed=0)

tests/pipelines/kandinsky/test_kandinsky_combined.py:280

↓ 3 callersMethodget_dummy_inputs

(self, device="cpu", seed=0)

tests/pipelines/paint_by_example/test_paint_by_example.py:101

↓ 3 callersMethodget_dummy_inputs

(self, device, seed=0)

tests/pipelines/wuerstchen/test_wuerstchen_combined.py:155

↓ 3 callersMethodget_dummy_inversion_inputs

(self, device, seed=0)

tests/pipelines/stable_diffusion/test_stable_diffusion_pix2pix_zero.py:148

↓ 3 callersMethodget_empty_store

()

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py:84

↓ 3 callersMethodget_extended_attention_mask

Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (

src/diffusers/pipelines/blip_diffusion/modeling_blip2.py:468

↓ 3 callersMethodget_generator

(self, seed=0)

tests/models/test_models_vae.py:582

↓ 3 callersMethodget_image_processor

(self, repo_id)

tests/pipelines/ip_adapters/test_ip_adapter_stable_diffusion.py:60

↓ 3 callersMethodget_inputs

(self, device, seed=0, generate_latents=False)

tests/pipelines/unidiffuser/test_unidiffuser.py:698

↓ 3 callersMethodget_inputs

(self, device, generator_device="cpu", dtype=torch.float32, seed=0)

tests/pipelines/stable_diffusion/test_stable_diffusion_image_variation.py:172

↓ 3 callersMethodget_inputs

(self, device, generator_device="cpu", dtype=torch.float32, seed=0)

tests/pipelines/audioldm2/test_audioldm2.py:501

↓ 3 callersFunctionget_model_modules

Get the model modules inside the transformers library.

utils/check_repo.py:231

↓ 3 callersFunctionget_models

Get the objects in module that are models.

utils/check_repo.py:270

↓ 3 callersMethodget_sd_vae_model

(self, model_id="hf-internal-testing/taesd-diffusers", fp16=False)

tests/models/test_models_vae.py:491

↓ 3 callersMethodload_lora_into_text_encoder

This will load the LoRA layers specified in `state_dict` into `text_encoder` Parameters: state_dict (`dict`):

src/diffusers/loaders/lora.py:473

↓ 3 callersMethodload_motion_modules

(self, motion_adapter: Optional[MotionAdapter])

src/diffusers/models/unet_motion_model.py:481

↓ 3 callersFunctionload_state_dict

Reads a checkpoint file, returning properly formatted errors if they arise.

src/diffusers/models/modeling_utils.py:103

↓ 3 callersFunctionmake_image_grid

Prepares a single grid of images. Useful for visualization purposes.

src/diffusers/utils/pil_utils.py:53

↓ 3 callersMethodmodel

(sample, t, *args)

tests/schedulers/test_schedulers.py:301

↓ 3 callersFunctionnumpy_to_pil

Convert a numpy image or a batch of images to a PIL image.

src/diffusers/utils/pil_utils.py:37

↓ 3 callersFunctionposenc_nerf

Concatenate x and its positional encodings, following NeRF. Reference: https://arxiv.org/pdf/2210.04628.pdf

src/diffusers/pipelines/shap_e/renderer.py:53

↓ 3 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py:393

↓ 3 callersMethodprepare_latents

(self, shape, dtype, device, generator, latents, scheduler)

src/diffusers/pipelines/unclip/pipeline_unclip.py:109

↓ 3 callersMethodprepare_latents

( self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py:463

↓ 3 callersMethodprevious_timestep

(self, timestep)

src/diffusers/schedulers/scheduling_lcm.py:619

↓ 3 callersFunctionrecurse_remove_peft_layers

r""" Recursively replace all instances of `LoraLayer` with corresponding new layers in `model`.

src/diffusers/utils/peft_utils.py:30

↓ 3 callersMethodremove_unused_weights

(self)

src/diffusers/pipelines/versatile_diffusion/pipeline_versatile_diffusion_dual_guided.py:106

↓ 3 callersFunctionrenew_attention_paths

Updates paths inside attentions to the new naming scheme (local renaming)

scripts/convert_original_audioldm2_to_diffusers.py:104

↓ 3 callersFunctionrenew_attention_paths

Updates paths inside attentions to the new naming scheme (local renaming)

scripts/convert_svd_to_diffusers.py:186

↓ 3 callersFunctionrenew_attention_paths

Updates paths inside attentions to the new naming scheme (local renaming)

scripts/convert_versatile_diffusion_to_diffusers.py:144

↓ 3 callersFunctionrenew_attention_paths

Updates paths inside attentions to the new naming scheme (local renaming)

scripts/convert_ldm_original_checkpoint_to_diffusers.py:57

↓ 3 callersFunctionrenew_attention_paths

Updates paths inside attentions to the new naming scheme (local renaming)

scripts/convert_original_audioldm_to_diffusers.py:97

↓ 3 callersFunctionrenew_attention_paths

Updates paths inside attentions to the new naming scheme (local renaming)

scripts/convert_zero123_to_diffusers.py:223

↓ 3 callersFunctionrenew_attention_paths

Updates paths inside attentions to the new naming scheme (local renaming)

scripts/convert_original_musicldm_to_diffusers.py:98

↓ 3 callersMethodreset_x0

(self, x_in, cond, act_dim)

src/diffusers/experimental/rl/value_guided_sampling.py:85

↓ 3 callersMethodreshape_heads_to_batch_dim

(self, tensor)

src/diffusers/models/attention_flax.py:165

↓ 3 callersMethodrun_safety_checker

(self, image, device, dtype)

src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py:483

↓ 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

src/diffusers/models/adapter.py:103

↓ 3 callersFunctionsegment

(a, n)

src/diffusers/pipelines/spectrogram_diffusion/midi_utils.py:339

↓ 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

src/diffusers/models/modeling_utils.py:342

↓ 3 callersFunctionset_attention_weights

(new_layer, old_checkpoint, index)

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

src/diffusers/models/unet_2d_condition.py:645

↓ 3 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

src/diffusers/loaders/lora.py:1218

↓ 3 callersMethodset_lora_layer

(self, lora_layer: Optional[LoRAConv2dLayer])

src/diffusers/models/lora.py:299

↓ 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

src/diffusers/schedulers/scheduling_sde_ve.py:125

↓ 3 callersMethodset_use_memory_efficient_attention_xformers

( self, valid: bool, attention_op: Optional[Callable] = None )

src/diffusers/pipelines/pipeline_utils.py:2027

↓ 3 callersMethodset_use_memory_efficient_attention_xformers

( self, valid: bool, attention_op: Optional[Callable] = None )

src/diffusers/models/modeling_utils.py:248

↓ 3 callersFunctionshave_segments

Removes segments. Positive values shave the first segments, negative shave the last segments.

scripts/convert_ms_text_to_video_to_diffusers.py:96

↓ 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

utils/custom_init_isort.py:142

↓ 3 callersFunctionsplit_attentions

(*, weight, bias, split, chunk_size)

scripts/convert_kandinsky_to_diffusers.py:838

↓ 3 callersFunctionsplit_attentions

(*, weight, bias, split, chunk_size)

scripts/convert_kakao_brain_unclip_to_diffusers.py:887

↓ 3 callersFunctionstate_dicts_almost_equal

(sd1, sd2)

tests/lora/test_lora_layers_peft.py:65

↓ 3 callersFunctionstate_dicts_almost_equal

(sd1, sd2)

tests/lora/test_lora_layers_old_backend.py:181

↓ 3 callersMethodtearDown

(self)

tests/models/test_models_vae.py:557

↓ 3 callersMethodto_torch

(self, x_in)

src/diffusers/experimental/rl/value_guided_sampling.py:78

↓ 3 callersMethodtranspose_for_scores

(self, projection: torch.Tensor)

src/diffusers/models/unet_1d_blocks.py:332

↓ 3 callersMethodtranspose_for_scores

(self, projection)

src/diffusers/models/vae_flax.py:232

↓ 3 callersFunctionunet_conv_in

(checkpoint, original_unet_prefix)

scripts/convert_kakao_brain_unclip_to_diffusers.py:584

↓ 3 callersFunctionunet_conv_norm_out

(checkpoint, original_unet_prefix)

scripts/convert_kakao_brain_unclip_to_diffusers.py:598

↓ 3 callersFunctionunet_conv_out

(checkpoint, original_unet_prefix)

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_

scripts/convert_kakao_brain_unclip_to_diffusers.py:626

↓ 3 callersFunctionunet_midblock_to_diffusers_checkpoint

(model, checkpoint, *, original_unet_prefix, num_head_channels)

scripts/convert_kakao_brain_unclip_to_diffusers.py:685

↓ 3 callersFunctionunet_time_embeddings

(checkpoint, original_unet_prefix)

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

scripts/convert_kakao_brain_unclip_to_diffusers.py:729

↓ 3 callersFunctionvalue_function

()

scripts/convert_models_diffuser_to_diffusers.py:59

↓ 2 callersMethod__init__

(self, config: CLIPTextConfig)

src/diffusers/pipelines/blip_diffusion/modeling_ctx_clip.py:47

↓ 2 callersMethod__init__

( self, unet: UNet2DConditionModel, scheduler: DDPMScheduler, movq: VQModel,

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_combined.py:139

↓ 2 callersMethod__init__

( self, text_encoder: MultilingualCLIP, tokenizer: XLMRobertaTokenizer, unet:

src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py:147

↓ 2 callersMethod__init__

(self, dim_in: int, dim_out: int, approximate: str = "none")

src/diffusers/models/activations.py:60

↓ 2 callersMethod__init__

( self, in_channels: int, layers_per_block: int = 2, num_attention_heads: int

src/diffusers/models/unet_motion_model.py:51

↓ 2 callersMethod__init__

(self, onnx_graph, verbose=False)

scripts/convert_stable_diffusion_controlnet_to_onnx.py:27

↓ 2 callersMethod_best_guess_weight_name

(cls, pretrained_model_name_or_path_or_dict, file_extension=".safetensors")

src/diffusers/loaders/lora.py:297

↓ 2 callersFunction_center_text

(text, width)

utils/check_table.py:81

↓ 2 callersMethod_clean_caption

(self, caption)

src/diffusers/pipelines/pixart_alpha/pipeline_pixart_alpha.py:502

↓ 2 callersMethod_clean_caption

(self, caption)

src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img_superresolution.py:235

↓ 2 callersMethod_clean_caption

(self, caption)

src/diffusers/pipelines/deepfloyd_if/pipeline_if.py:441

↓ 2 callersMethod_clean_caption

(self, caption)

src/diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py:193

↓ 2 callersMethod_clean_caption

(self, caption)

src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py:486

↓ 2 callersMethod_clean_caption

(self, caption)

src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py:237

↓ 2 callersMethod_clean_caption

(self, caption)

src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting.py:526

↓ 2 callersFunction_compare_versions

(op, got_ver, want_ver, requirement, pkg, hint)

src/diffusers/utils/versions.py:37

↓ 2 callersMethod_convert_deprecated_attention_blocks

(self, state_dict: OrderedDict)

src/diffusers/models/modeling_utils.py:1074

↓ 2 callersMethod_convert_to_karras

Constructs the noise schedule of Karras et al. (2022).

src/diffusers/schedulers/scheduling_consistency_models.py:235

↓ 2 callersMethod_cumsum

(self, input, dim, debug=False)

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_paradigms.py:501

↓ 2 callersMethod_decode

(self, z: torch.FloatTensor, return_dict: bool = True)

src/diffusers/models/autoencoder_kl.py:269

↓ 2 callersMethod_dict_from_json_file

(cls, json_file: Union[str, os.PathLike])

src/diffusers/configuration_utils.py:544

↓ 2 callersMethod_downsample_2d

Fused `Conv2d()` followed by `downsample_2d()`. Padding is performed only once at the beginning, not between the operations. The fused op is c

src/diffusers/models/resnet.py:447

↓ 2 callersMethod_encode_image

( self, image: Union[torch.Tensor, List[PIL.Image.Image]], device, num_images_

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_prior_emb2emb.py:245

↓ 2 callersMethod_encode_vae_image

(self, image: torch.Tensor, generator: torch.Generator)

src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py:863

↓ 2 callersMethod_encode_vae_image

(self, image: torch.Tensor, generator: torch.Generator)

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py:833

↓ 2 callersMethod_encode_vae_image

(self, image: torch.Tensor, generator: torch.Generator)

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py:988

↓ 2 callersFunction_filter2d

(input, kernel)

src/diffusers/pipelines/stable_video_diffusion/pipeline_stable_video_diffusion.py:597

↓ 2 callersFunction_gaussian

(window_size: int, sigma)

src/diffusers/pipelines/stable_video_diffusion/pipeline_stable_video_diffusion.py:620

↓ 2 callersMethod_generate

( self, prompt_ids: jnp.array, params: Union[Dict, FrozenDict], prng_seed: jax

src/diffusers/pipelines/stable_diffusion_xl/pipeline_flax_stable_diffusion_xl.py:169

↓ 2 callersMethod_generate

( self, prompt_ids: jnp.ndarray, image: jnp.ndarray, params: Union[Dict, Froze

src/diffusers/pipelines/controlnet/pipeline_flax_controlnet.py:239

↓ 2 callersMethod_generate

( self, prompt_ids: jnp.ndarray, mask: jnp.ndarray, masked_image: jnp.ndarray,

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_inpaint.py:267

↓ 2 callersMethod_generate

( self, prompt_ids: jnp.ndarray, image: jnp.ndarray, params: Union[Dict, Froze

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_img2img.py:233

← previous next →601–700 of 7,383, ranked by callers