Functions — github.com/bytedance/StyleSSP

CodeHub MCPcopy Create free account

hub / github.com/bytedance/StyleSSP / functions

Functions440 in github.com/bytedance/StyleSSP

⨍ Functions 440◇ Types & classes 84

↓ 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

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:85

↓ 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

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:62

↓ 1 callersFunctionretrieve_timesteps

Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:100

↓ 1 callersFunctionretrieve_timesteps

Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs

ip_adapter/pipeline_stable_diffusion_sd3_extra_cfg.py:76

↓ 1 callersFunctionrun

(init_image: Image, prompt: str, cfg: RunConfig, pipe_inversion, pipe_inferenc

inversion.py:37

↓ 1 callersMethodrun_safety_checker

(self, image, device, dtype)

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:580

↓ 1 callersFunctionscheduler_type_to_class

(scheduler_type)

src/utils/enums_utils.py:16

↓ 1 callersMethodset_ip_adapter

ip_adapter/ip_adapter_instruct.py:731

↓ 1 callersMethodset_ip_adapter

(self,dtype=torch.float16)

ip_adapter/ip_adapter.py:100

↓ 1 callersFunctionset_requires_grad

pipeline_controlnet_inpaint_sd_xl.py:92

↓ 1 callersFunctionset_requires_grad

pipeline_controlnet_sd_xl_img2img_plus.py:171

↓ 1 callersMethodset_scale

ip_adapter/ip_adapter_instruct.py:814

↓ 1 callersFunctionslerp

taken from https://discuss.pytorch.org/t/help-regarding-slerp-function-for-generative-model-sampling/32475/4

src/utils/images_utils.py:79

↓ 1 callersMethodstep_and_update_noise

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

src/schedulers/euler_scheduler.py:163

↓ 1 callersMethodupcast_vae

pipeline_controlnet_inpaint_sd_xl.py:1292

↓ 1 callersMethodupcast_vae

pipeline_controlnet_sd_xl_img2img_plus.py:1111

↓ 1 callersMethodupcast_vae

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:748

↓ 1 callersFunctionupscale

(attn_map, target_size)

ip_adapter/utils.py:25

↓ 1 callersMethodz_score

(self, x: torch.Tensor)

src/metrics/lpips.py:40

FunctionFourier_filter

(x, threshold, scale)

src/renoise_inversion.py:79

FunctionFourier_filter

(x, threshold, scale)

src/frequency_utils.py:430

FunctionGaussian_highpass_filter

(x, sigma = 5, amp = 0.5)

src/frequency_utils.py:452

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):

pipeline_controlnet_inpaint_sd_xl.py:1335

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):

pipeline_controlnet_sd_xl_img2img_plus.py:1247

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):

pipeline_controlnet_sd_xl_img2img.py:1030

( self, attn, hidden_states, encoder_hidden_states=None, attention_mas

ip_adapter/attention_processor.py:23

( self, attn, hidden_states, encoder_hidden_states=None, attention_mas

ip_adapter/attention_processor.py:109

( self, attn, hidden_states, encoder_hidden_states=None, attention_mas

ip_adapter/attention_processor.py:205

( self, attn, hidden_states, encoder_hidden_states=None, attention_mas

ip_adapter/attention_processor.py:308

(self, attn, hidden_states, encoder_hidden_states=None, attention_mask=None, temb=None)

ip_adapter/attention_processor.py:420

( self, attn, hidden_states, encoder_hidden_states=None, attention_mas

ip_adapter/attention_processor.py:487

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:834

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):

ip_adapter/pipeline_stable_diffusion_sd3_extra_cfg.py:684

r""" The call function to the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*): T

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:777

( self, attn: Attention, hidden_states: torch.FloatTensor, encoder_hidden_stat

ip_adapter/ip_joint_attention.py:44

( self, attn: Attention, hidden_states: torch.FloatTensor, encoder_hidden_stat

ip_adapter/ip_joint_attention.py:162

( self, prompt: Union[str, List[str]] = None, prompt_2: Optional[Union[str, List[str]]

src/pipes/sdxl_inversion_pipeline.py:21

( self, prompt: Union[str, List[str]] = None, image: PipelineImageInput = None,

src/pipes/sd_inversion_pipeline.py:20

Method__getitem__

evaluation/eval_artfid.py:34

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, text_encoder_2: CLIPT

pipeline_controlnet_inpaint_sd_xl.py:236

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, text_encoder_2: CLIPT

pipeline_controlnet_sd_xl_img2img_plus.py:255

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, text_encoder_2: CLIPT

pipeline_controlnet_sd_xl_img2img.py:259

(self, hidden_size, cross_attention_dim=None, scale=1.0, num_tokens=4)

ip_adapter/attention_processor.py:98

( self, hidden_size=None, cross_attention_dim=None, )

ip_adapter/attention_processor.py:196

(self, hidden_size, cross_attention_dim=None, scale=1.0, num_tokens=4)

ip_adapter/attention_processor.py:294

(self, num_tokens=4)

ip_adapter/attention_processor.py:417

(self, num_tokens=4)

ip_adapter/attention_processor.py:482

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, text_encoder_2: CLIPT

ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py:231

( self, transformer: SD3Transformer2DModel, scheduler: FlowMatchEulerDiscreteScheduler

ip_adapter/pipeline_stable_diffusion_sd3_extra_cfg.py:173

(self, *, dim, dim_head=64, heads=8)

ip_adapter/resampler_Instruct.py:106

(self, *, dim, dim_head=64, heads=8)

ip_adapter/resampler_Instruct.py:153

( self, dim=1024, depth=4, dim_head=64, heads=16, num_queries=

ip_adapter/resampler_Instruct.py:199

( self, dim=1024, depth=4, dim_head=64, heads=16, num_queries=

ip_adapter/resampler_Instruct.py:272

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, tokenizer: CLIPTokeni

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:181

(self, hidden_size,cross_attention_dim, scale=1.0, num_tokens=8,num_heads=12)

ip_adapter/ip_joint_attention.py:21

(self, *, dim, dim_head=64, heads=8)

ip_adapter/resampler_SD3.py:37

( self, dim=1024, depth=8, dim_head=64, heads=16, num_queries=

ip_adapter/resampler_SD3.py:172

(self, *, dim, dim_head=64, heads=8)

ip_adapter/resampler.py:37

(self, sd_pipe, image_encoder_path, ip_ckpt, device, num_tokens=4, dtypein=torch.float32)

ip_adapter/ip_adapter_instruct.py:38

(self, sd_pipe, image_encoder_path, ip_ckpt, device, num_tokens=4)

ip_adapter/ip_adapter_instruct.py:491

(self, sd_pipe, image_encoder_path, ip_ckpt, device, num_tokens=4)

ip_adapter/ip_adapter_instruct.py:689

(self, cross_attention_dim=1024, clip_embeddings_dim=1024, clip_extra_context_tokens=4)

ip_adapter/ip_adapter.py:36

(self, cross_attention_dim=1024, clip_embeddings_dim=1024)

ip_adapter/ip_adapter.py:56

(self, encoder, gpu_ids=[])

src/evaluate/net.py:65

(self, metric_type='vgg')

src/evaluate/image_metrics.py:36

src/evaluate/image_metrics.py:79

(self, device=None)

src/evaluate/image_metrics.py:90

(self, device=None)

src/evaluate/image_metrics.py:137

( self, in_channels: int, pool_features: int, conv_block: Optional[Callable[..., nn.Module]] = None

src/evaluate/inception.py:173

(self, in_channels: int, conv_block: Optional[Callable[..., nn.Module]] = None)

src/evaluate/inception.py:212

( self, in_channels: int, channels_7x7: int, conv_block: Optional[Callable[..., nn.Module]] = None

src/evaluate/inception.py:240

(self, in_channels: int, conv_block: Optional[Callable[..., nn.Module]] = None)

src/evaluate/inception.py:286

(self, in_channels: int, conv_block: Optional[Callable[..., nn.Module]] = None)

src/evaluate/inception.py:317

( self, in_channels: int, num_classes: int, conv_block: Optional[Callable[..., nn.Module]] = None

src/evaluate/inception.py:364

(self, in_channels: int, out_channels: int, **kwargs: Any)

src/evaluate/inception.py:395

src/metrics/lpips.py:27

src/metrics/lpips.py:57

src/metrics/lpips.py:68

(self, n_channels_list: Sequence[int])

src/metrics/lpips.py:89

(self, net_type: str = 'vgg', version: str = '0.1')

src/metrics/lpips.py:130

(self, files, transforms=None)

evaluation/eval_artfid.py:27

(self, encoder, gpu_ids=[])

evaluation/net.py:65

(self, metric_type='vgg')

evaluation/image_metrics.py:36

evaluation/image_metrics.py:79

(self, device=None)

evaluation/image_metrics.py:90

(self, device=None)

evaluation/image_metrics.py:137

( self, in_channels: int, pool_features: int, conv_block: Optional[Callable[..., nn.Module]] = None

evaluation/inception.py:173

(self, in_channels: int, conv_block: Optional[Callable[..., nn.Module]] = None)

evaluation/inception.py:212

( self, in_channels: int, channels_7x7: int, conv_block: Optional[Callable[..., nn.Module]] = None

evaluation/inception.py:240

(self, in_channels: int, conv_block: Optional[Callable[..., nn.Module]] = None)

evaluation/inception.py:286

(self, in_channels: int, conv_block: Optional[Callable[..., nn.Module]] = None)

evaluation/inception.py:317

( self, in_channels: int, num_classes: int, conv_block: Optional[Callable[..., nn.Module]] = None

evaluation/inception.py:364

(self, in_channels: int, out_channels: int, **kwargs: Any)

evaluation/inception.py:395

evaluation/eval_artfid.py:31

Method__post_init__

src/config.py:71

Method_encode_prompt

( self, prompt, device, num_images_per_prompt, do_classifier_free_guid

ip_adapter/pipeline_stable_diffusion_extra_cfg.py:273

Method_initialize_weights

ip_adapter/resampler_Instruct.py:43

Methodadd_noise_off_schedule

( self, original_samples: torch.FloatTensor, noise: torch.FloatTensor, timeste

src/schedulers/euler_scheduler.py:393

Functionattnmaps2images

(net_attn_maps)

ip_adapter/utils.py:64

Functioncalc_mean_std

(feat, eps=1e-5)

src/evaluate/image_metrics.py:17

← previous next →201–300 of 440, ranked by callers