Functions — github.com/Shakker-Labs/RepText

↓ 4 callersMethod_pack_latents

(latents, batch_size, num_channels_latents, height, width)

pipeline_flux_controlnet_inpaint.py:542

↓ 4 callersMethod_prepare_latent_image_ids

(batch_size, height, width, device, dtype)

pipeline_flux_controlnet.py:535

↓ 4 callersMethod_prepare_latent_image_ids

(batch_size, height, width, device, dtype)

pipeline_flux_controlnet_inpaint.py:527

↓ 3 callersMethod_pack_latents

(latents, batch_size, num_channels_latents, height, width)

pipeline_flux_controlnet.py:550

↓ 2 callersMethod_get_clip_prompt_embeds

( self, prompt: Union[str, List[str]], num_images_per_prompt: int = 1, device:

pipeline_flux_controlnet_inpaint.py:292

↓ 2 callersMethod_get_t5_prompt_embeds

( self, prompt: Union[str, List[str]] = None, num_images_per_prompt: int = 1,

pipeline_flux_controlnet.py:232

↓ 2 callersMethod_get_t5_prompt_embeds

( self, prompt: Union[str, List[str]] = None, num_images_per_prompt: int = 1,

pipeline_flux_controlnet_inpaint.py:244

↓ 2 callersFunctionretrieve_latents

( encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample" )

pipeline_flux_controlnet.py:91

↓ 2 callersFunctionretrieve_latents

( encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample" )

pipeline_flux_controlnet_inpaint.py:92

↓ 1 callersMethod__init__

( self, patch_size: int = 1, in_channels: int = 64, num_layers: int = 19,

controlnet_flux.py:45

↓ 1 callersMethod_encode_vae_image

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

pipeline_flux_controlnet.py:459

↓ 1 callersMethod_encode_vae_image

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

pipeline_flux_controlnet_inpaint.py:451

↓ 1 callersMethod_get_clip_prompt_embeds

( self, prompt: Union[str, List[str]], num_images_per_prompt: int = 1, device:

pipeline_flux_controlnet.py:308

↓ 1 callersMethod_unpack_latents

(latents, height, width, vae_scale_factor)

pipeline_flux_controlnet.py:559

↓ 1 callersMethod_unpack_latents

(latents, height, width, vae_scale_factor)

pipeline_flux_controlnet_inpaint.py:551

↓ 1 callersFunctioncalculate_shift

( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_shift: float = 0.5,

pipeline_flux_controlnet.py:78

↓ 1 callersFunctioncalculate_shift

( image_seq_len, base_seq_len: int = 256, max_seq_len: int = 4096, base_shift: float = 0.5,

pipeline_flux_controlnet_inpaint.py:79

↓ 1 callersFunctioncanny

(img)

infer.py:16

↓ 1 callersFunctioncanny

(img)

infer_inpaint.py:17

↓ 1 callersMethodcheck_inputs

( self, prompt, prompt_2, height, width, prompt_embeds=None,

pipeline_flux_controlnet.py:485

↓ 1 callersMethodcheck_inputs

( self, prompt, prompt_2, height, width, prompt_embeds=None,

pipeline_flux_controlnet_inpaint.py:477

↓ 1 callersFunctioncontains_chinese

(text)

infer.py:11

↓ 1 callersFunctioncontains_chinese

(text)

infer_inpaint.py:12

↓ 1 callersMethodencode_prompt

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

pipeline_flux_controlnet.py:349

↓ 1 callersMethodencode_prompt

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

pipeline_flux_controlnet_inpaint.py:333

↓ 1 callersMethodprepare_image

( self, image, width, height, batch_size, num_images_per_promp

pipeline_flux_controlnet.py:663

↓ 1 callersMethodprepare_image

( self, image, width, height, batch_size, num_images_per_promp

pipeline_flux_controlnet_inpaint.py:656

↓ 1 callersMethodprepare_image_with_mask

( self, image, mask, width, height, batch_size, num_im

pipeline_flux_controlnet_inpaint.py:761

↓ 1 callersMethodprepare_latents

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

pipeline_flux_controlnet.py:573

↓ 1 callersMethodprepare_latents

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

pipeline_flux_controlnet_inpaint.py:565

↓ 1 callersMethodprepare_latents_reptext

( self, image, batch_size, num_channels_latents, height, width

pipeline_flux_controlnet.py:608

↓ 1 callersMethodprepare_latents_reptext

( self, image, batch_size, num_channels_latents, height, width

pipeline_flux_controlnet_inpaint.py:600

↓ 1 callersFunctionresize_img

(input_image, max_side=1280, min_side=1024, size=None, pad_to_max_side=False, mode=Image.BILIN

infer_inpaint.py:25

↓ 1 callersFunctionretrieve_timesteps

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

pipeline_flux_controlnet.py:104

↓ 1 callersFunctionretrieve_timesteps

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

pipeline_flux_controlnet_inpaint.py:105

Method__call__

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

pipeline_flux_controlnet.py:751

Method__call__

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

pipeline_flux_controlnet_inpaint.py:846

Method__init__

(self, controlnets, union=False)

controlnet_flux.py:429

Method__init__

( self, scheduler: FlowMatchEulerDiscreteScheduler, vae: AutoencoderKL, text_e

pipeline_flux_controlnet.py:194

Method__init__

( self, scheduler: FlowMatchEulerDiscreteScheduler, vae: AutoencoderKL, text_e

pipeline_flux_controlnet_inpaint.py:195

Method_set_gradient_checkpointing

(self, module, value=False)

controlnet_flux.py:178

Methodattn_processors

r""" Returns: `dict` of attention processors: A dictionary containing all attention processors used in the model with

controlnet_flux.py:120

Methodcreate_custom_forward

(module, return_dict=None)

controlnet_flux.py:323

Methodcustom_forward

(*inputs)

controlnet_flux.py:324

Methoddo_classifier_free_guidance

(self)

pipeline_flux_controlnet.py:229

Methoddo_classifier_free_guidance

(self)

pipeline_flux_controlnet_inpaint.py:241

Functionextract_dwpose

(img, include_body=True, include_hand=True, include_face=True)

infer_inpaint.py:48

Methodfn_recursive_add_processors

(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor])

controlnet_flux.py:129

Methodfn_recursive_attn_processor

(name: str, module: torch.nn.Module, processor)

controlnet_flux.py:165

Methodforward

The [`FluxTransformer2DModel`] forward method. Args: hidden_states (`torch.FloatTensor` of shape `(batch size, channel,

controlnet_flux.py:216

Methodforward

( self, hidden_states: torch.FloatTensor, controlnet_cond: List[torch.tensor],

controlnet_flux.py:434

Methodfrom_transformer

( cls, transformer, num_layers: int = 4, num_single_layers: int = 10,

controlnet_flux.py:183

Methodget_timesteps

(self, num_inference_steps, strength, device)

pipeline_flux_controlnet.py:474

Methodget_timesteps

(self, num_inference_steps, strength, device)

pipeline_flux_controlnet_inpaint.py:466

Methodguidance_scale

(self)

pipeline_flux_controlnet.py:734

Methodguidance_scale

(self)

pipeline_flux_controlnet_inpaint.py:829

Methodinterrupt

(self)

pipeline_flux_controlnet.py:746

Methodinterrupt

(self)

pipeline_flux_controlnet_inpaint.py:841

Methodjoint_attention_kwargs

(self)

pipeline_flux_controlnet.py:738

Methodjoint_attention_kwargs

(self)

pipeline_flux_controlnet_inpaint.py:833

Methodnum_timesteps

(self)

pipeline_flux_controlnet.py:742

Methodnum_timesteps

(self)

pipeline_flux_controlnet_inpaint.py:837

Methodprepare_image_union

( self, image, width, height, batch_size, num_images_per_promp

pipeline_flux_controlnet_inpaint.py:727

Methodset_attn_processor

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

controlnet_flux.py:144

Functions64 in github.com/Shakker-Labs/RepText