Functions — github.com/bytedance/StyleSSP

hub / github.com/bytedance/StyleSSP / functions

Functions440 in github.com/bytedance/StyleSSP

⨍ Functions 440◇ Types & classes 84

↓ 1 callersMethod_forward

(self, x: Tensor)

evaluation/inception.py:222

↓ 1 callersMethod_forward

(self, x: Tensor)

evaluation/inception.py:261

↓ 1 callersMethod_forward

(self, x: Tensor)

evaluation/inception.py:298

↓ 1 callersMethod_forward

(self, x: Tensor)

evaluation/inception.py:334

↓ 1 callersMethod_get_add_time_ids

( self, original_size, crops_coords_top_left, target_size, aesthetic_s

pipeline_controlnet_inpaint_sd_xl.py:1245

↓ 1 callersMethod_get_add_time_ids

( self, original_size, crops_coords_top_left, target_size, aesthetic_s

pipeline_controlnet_sd_xl_img2img_plus.py:1059

↓ 1 callersFunction_get_pipes

(model_type, device, model_name=None)

src/utils/enums_utils.py:128

↓ 1 callersMethod_transform_input

(self, x: Tensor)

src/evaluate/inception.py:84

↓ 1 callersMethod_transform_input

(self, x: Tensor)

evaluation/inception.py:84

↓ 1 callersMethodadain

(self, content_feat, style_feat)

src/evaluate/net.py:98

↓ 1 callersMethodadain

(self, content_feat, style_feat)

evaluation/net.py:98

↓ 1 callersFunctionauto_corr_loss

( x, random_shift=True, generator=None )

src/renoise_inversion.py:36

↓ 1 callersFunctionbox_low_pass_filter

Compute the ideal low pass filter mask (approximated version). Args: shape: shape of the filter (volume) d_s: normalized sto

src/frequency_utils.py:303

↓ 1 callersFunctionbutterworth_low_pass_filter

Compute the butterworth low pass filter mask. Args: shape: shape of the filter (volume) n: order of the filter, larger n ~ i

src/frequency_utils.py:262

↓ 1 callersFunctioncalculate_l2_difference

(image1, image2, device = 'cuda')

src/metrics/metric_util.py:15

↓ 1 callersFunctioncalculate_lpips

(image1, image2, device = 'cuda')

src/metrics/metric_util.py:38

↓ 1 callersFunctioncalculate_psnr

(image1, image2, device = 'cuda')

src/metrics/metric_util.py:24

↓ 1 callersMethodcheck_inputs

( self, prompt, prompt_2, image, mask_image, strength,

pipeline_controlnet_inpaint_sd_xl.py:806

↓ 1 callersMethodcheck_inputs

( self, prompt, prompt_2, image, strength, num_inference_steps

pipeline_controlnet_sd_xl_img2img_plus.py:649

↓ 1 callersMethodcheck_inputs

( self, prompt, prompt_2, height, width, callback_steps,

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:611

↓ 1 callersMethodcheck_inputs

( self, prompt, prompt_2, prompt_3, height, width, neg

ip_adapter/pipeline_stable_diffusion_sd3_extra_cfg.py:534

↓ 1 callersMethodcheck_inputs

( self, prompt, height, width, callback_steps, negative_prompt

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:622

↓ 1 callersFunctioncompute_art_fid

Computes the FID for the given paths. Args: path_to_stylized (str): Path to the stylized images. path_to_style (str): Path to the

evaluation/eval_artfid.py:392

↓ 1 callersFunctioncompute_fid

Computes the FID for the given paths. Args: path_to_stylized (str): Path to the stylized images. path_to_style (str): Path to the

evaluation/eval_artfid.py:176

↓ 1 callersFunctioncompute_fid_infinity

Computes the FID infinity for the given paths. Args: path_to_stylized (str): Path to the stylized images. path_to_style (str): Pa

evaluation/eval_artfid.py:208

↓ 1 callersFunctioncompute_patch_simi

Computes the distance for the given paths. Args: path_to_stylized (str): Path to the stylized images. path_to_style (str): Path t

evaluation/eval_artfid.py:336

↓ 1 callersMethodcond_fn

( self, latents, timestep, index, prompt_embeds, down_block_re

pipeline_controlnet_inpaint_sd_xl.py:654

↓ 1 callersMethodcond_fn

( self, latents, timestep, index, prompt_embeds, down_block_re

pipeline_controlnet_sd_xl_img2img_plus.py:1162

↓ 1 callersFunctioncreate_noise_list

(model_type, length, generator=None)

inversion.py:27

↓ 1 callersMethodeager_outputs

(self, out1: Tensor, out2: Tensor, aux1: Optional[Tensor], aux2: Optional[Tensor])

src/evaluate/inception.py:152

↓ 1 callersMethodeager_outputs

(self, out1: Tensor, out2: Tensor, aux1: Optional[Tensor], aux2: Optional[Tensor])

evaluation/inception.py:152

↓ 1 callersMethodencode_image

(self, image, device, num_images_per_prompt, output_hidden_states=None)

pipeline_controlnet_inpaint_sd_xl.py:561

↓ 1 callersMethodencode_image

(self, image, device, num_images_per_prompt, output_hidden_states=None)

pipeline_controlnet_sd_xl_img2img_plus.py:555

↓ 1 callersMethodencode_image

(self, image, device, num_images_per_prompt, output_hidden_states=None)

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:523

↓ 1 callersMethodencode_image

(self, image, device, num_images_per_prompt, output_hidden_states=None)

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:505

↓ 1 callersMethodencode_prompt

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

pipeline_controlnet_inpaint_sd_xl.py:307

↓ 1 callersMethodencode_prompt

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

pipeline_controlnet_sd_xl_img2img_plus.py:320

↓ 1 callersMethodencode_prompt

r""" Args: prompt (`str` or `List[str]`, *optional*): prompt to be encoded prompt_2 (`str` or `List[s

ip_adapter/pipeline_stable_diffusion_sd3_extra_cfg.py:322

↓ 1 callersFunctionfreq_exp

Frequency manipulation for latent space, maintain the high frequency part of content image and low frequency part of style image. n: (only fo

src/frequency_utils.py:379

↓ 1 callersFunctiongaussian_band_pass_filter

Compute the Gaussian band-pass filter mask. Consider that the highest part of image is noise. Filter it as well as filter the low-fre

src/frequency_utils.py:234

↓ 1 callersFunctiongaussian_low_pass_filter

Compute the gaussian low pass filter mask. Args: shape: shape of the filter (volume) d_s: normalized stop frequency for spat

src/frequency_utils.py:214

↓ 1 callersMethodget_all_sigmas

(self)

src/schedulers/euler_scheduler.py:388

↓ 1 callersFunctionget_guidace

(pipe_inf, latents, prompt, feature_extractor,

src/renoise_inversion.py:264

↓ 1 callersMethodget_guidance_scale_embedding

See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298 Args: w (`tor

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:767

↓ 1 callersMethodget_guidance_scale_embedding

See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298 Args: w (`tor

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:714

↓ 1 callersMethodget_image_embeds

(self, pil_image=None, clip_image_embeds=None,instruct_embeds=None,negative_instruct_embeds=None,prompt_embeds

ip_adapter/ip_adapter_instruct.py:96

↓ 1 callersMethodget_image_embeds

(self, pil_image=None, clip_image_embeds=None,instruct_embeds=None,negative_instruct_embeds=None,prompt_embeds

ip_adapter/ip_adapter_instruct.py:793

↓ 1 callersMethodget_image_embeds

(self, pil_image)

ip_adapter/ip_adapter.py:351

↓ 1 callersFunctionget_network

(net_type: str = 'vgg')

src/metrics/lpips.py:12

↓ 1 callersFunctionget_pipes

(model_type, scheduler_type, device="cuda", model_name=None)

src/utils/enums_utils.py:152

↓ 1 callersFunctionget_state_dict

(net_type: str = 'alex', version: str = '0.1')

src/metrics/lpips.py:101

↓ 1 callersMethodget_timesteps

(self, num_inference_steps, strength, device, denoising_start=None)

pipeline_controlnet_inpaint_sd_xl.py:1209

↓ 1 callersMethodget_timesteps

(self, num_inference_steps, strength, device, denoising_start=None)

pipeline_controlnet_sd_xl_img2img_plus.py:920

↓ 1 callersFunctionhook_fn

(name)

ip_adapter/utils.py:10

↓ 1 callersFunctionideal_low_pass_filter

Compute the ideal low pass filter mask. Args: shape: shape of the filter (volume) d_s: normalized stop frequency for spatial

src/frequency_utils.py:283

↓ 1 callersFunctioninit_models

(config)

infer_style.py:139

↓ 1 callersMethodinit_proj

(self)

ip_adapter/ip_adapter_instruct.py:79

↓ 1 callersMethodinit_proj

(self)

ip_adapter/ip_adapter_instruct.py:517

↓ 1 callersMethodinit_proj

(self)

ip_adapter/ip_adapter_instruct.py:717

↓ 1 callersMethodinit_proj

(self)

ip_adapter/ip_adapter.py:92

↓ 1 callersFunctionis_float16

(model_type)

src/utils/enums_utils.py:92

↓ 1 callersFunctionis_sd

(model_type)

src/utils/enums_utils.py:110

↓ 1 callersFunctionis_stochastic

(scheduler_type)

src/utils/enums_utils.py:26

↓ 1 callersFunctionis_torch2_available

()

ip_adapter/utils.py:83

↓ 1 callersFunctionlatents_kl_divergence

(x0, x1)

src/renoise_inversion.py:106

↓ 1 callersMethodload_ip_adapter

(self)

ip_adapter/ip_adapter_instruct.py:62

↓ 1 callersMethodload_ip_adapter

(self)

ip_adapter/ip_adapter_instruct.py:572

↓ 1 callersMethodload_ip_adapter

(self)

ip_adapter/ip_adapter_instruct.py:773

↓ 1 callersFunctionmain

(cfg: RunConfig)

inversion.py:34

↓ 1 callersFunctionmain

()

evaluation/eval_artfid.py:447

↓ 1 callersFunctionmasked_mean

(t, *, dim, mask=None)

ip_adapter/resampler_SD3.py:160

↓ 1 callersFunctionmasked_mean

(t, *, dim, mask=None)

ip_adapter/resampler.py:152

↓ 1 callersFunctionmodel_type_to_class

(model_type)

src/utils/enums_utils.py:36

↓ 1 callersFunctionmodel_type_to_model_name

(model_type)

src/utils/enums_utils.py:54

↓ 1 callersFunctionmodel_type_to_size

(model_type)

src/utils/enums_utils.py:74

↓ 1 callersFunctionnormalize_activation

(x, eps=1e-10)

src/metrics/lpips.py:22

↓ 1 callersMethodpatch_simi_cnt

(self, input)

src/evaluate/image_metrics.py:111

↓ 1 callersMethodpatch_simi_cnt

(self, input)

evaluation/image_metrics.py:111

↓ 1 callersMethodpatch_simi_out

(self, input)

src/evaluate/image_metrics.py:119

↓ 1 callersMethodpatch_simi_out

(self, input)

evaluation/image_metrics.py:119

↓ 1 callersFunctionpatchify_latents_kl_divergence

(x0, x1, patch_size=4, num_channels=4)

src/renoise_inversion.py:62

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

pipeline_controlnet_inpaint_sd_xl.py:635

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

pipeline_controlnet_sd_xl_img2img_plus.py:632

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:594

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:605

↓ 1 callersMethodprepare_ip_adapter_image_embeds

( self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_g

pipeline_controlnet_inpaint_sd_xl.py:586

↓ 1 callersMethodprepare_ip_adapter_image_embeds

( self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_g

pipeline_controlnet_sd_xl_img2img_plus.py:580

↓ 1 callersMethodprepare_ip_adapter_image_embeds

( self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_g

pipeline_controlnet_sd_xl_img2img.py:790

↓ 1 callersMethodprepare_ip_adapter_image_embeds

( self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_g

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:548

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, height, width, dtype

pipeline_controlnet_inpaint_sd_xl.py:1057

↓ 1 callersMethodprepare_latents

( self, image, timestep, batch_size, num_images_per_prompt, dtype, device, generator=None, add_noise=T

pipeline_controlnet_sd_xl_img2img_plus.py:979

↓ 1 callersMethodprepare_latents

(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None)

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:708

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, height, width, dtype

ip_adapter/pipeline_stable_diffusion_sd3_extra_cfg.py:624

↓ 1 callersMethodprepare_latents

(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None)

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:691

↓ 1 callersMethodprepare_latents_t2i

(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None)

pipeline_controlnet_sd_xl_img2img_plus.py:956

↓ 1 callersMethodprepare_mask_latents

( self, mask, masked_image, batch_size, height, width, dtype, device, generator, do_classifier_free_gu

pipeline_controlnet_inpaint_sd_xl.py:1161

↓ 1 callersFunctionrescale_guidance

(guidance, noise_pred_text, noise_pred_uncond, guidance_scale, cutoff = 2000.0)

src/renoise_inversion.py:256

↓ 1 callersMethodrescale_guidance

(self, guidance, noise_pred_text, noise_pred_uncond, guidance_scale)

pipeline_controlnet_inpaint_sd_xl.py:764

↓ 1 callersFunctionrescale_noise_cfg

Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and Sample Steps are Flawed](http

pipeline_controlnet_inpaint_sd_xl.py:154

↓ 1 callersFunctionrescale_noise_cfg

Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and Sample Steps are Flawed](http

pipeline_controlnet_sd_xl_img2img.py:96

← previous next →101–200 of 440, ranked by callers