MCPcopy Create free account

hub / github.com/horseee/DeepCache / functions

Functions1,211 in github.com/horseee/DeepCache

⨍ Functions 1,211◇ Types & classes 220
↓ 3 callersFunctioncustom_to_pil
(x)
experiments/ldm/scripts/sample_diffusion.py:15
↓ 3 callersFunctiondefault
(val, d)
experiments/ldm/ldm/modules/attention.py:19
↓ 3 callersMethodema
(self, module)
experiments/ddpm/ddpm/models/ema.py:25
↓ 3 callersMethodenable_model_cpu_offload
r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti
DeepCache/sdxl/pipeline_utils.py:1231
↓ 3 callersFunctionexists
(val)
experiments/ldm/ldm/modules/attention.py:11
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
experiments/ldm/ldm/modules/image_degradation/bsrgan_light.py:210
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:210
↓ 3 callersFunctionget_ckpt_path
(name, root=None, check=False)
experiments/ddpm/ddpm/functions/ckpt_util.py:55
↓ 3 callersMethodget_input
(self, batch, k)
experiments/ldm/ldm/models/autoencoder.py:344
↓ 3 callersMethodget_loss
(self, pred, target, mean=True)
experiments/ldm/ldm/models/diffusion/ddpm.py:279
↓ 3 callersFunctionget_model_parameters_number
(model)
DeepCache/flops.py:390
↓ 3 callersMethodget_weighting
(self, h, w, Ly, Lx, device)
experiments/ldm/ldm/models/diffusion/ddpm.py:585
↓ 3 callersFunctionismap
(x)
experiments/ldm/ldm/util.py:41
↓ 3 callersFunctionlog_txt_as_img
(wh, xc, size=10)
experiments/ldm/ldm/util.py:17
↓ 3 callersMethodpreprocess
(self, x)
experiments/ldm/ldm/modules/encoders/modules.py:189
↓ 3 callersMethodregister
(self, module)
experiments/ddpm/ddpm/models/ema.py:10
↓ 3 callersMethodset_use_memory_efficient_attention_xformers
( self, valid: bool, attention_op: Optional[Callable] = None )
DeepCache/sdxl/pipeline_utils.py:1763
↓ 3 callersMethodset_use_memory_efficient_attention_xformers
( self, valid: bool, attention_op: Optional[Callable] = None )
DeepCache/svd/pipeline_utils.py:2030
↓ 3 callersMethodset_use_memory_efficient_attention_xformers
( self, valid: bool, attention_op: Optional[Callable] = None )
DeepCache/sd/pipeline_utils.py:1763
↓ 3 callersMethodshared_step
(self, batch)
experiments/ldm/ldm/models/diffusion/ddpm.py:337
↓ 3 callersFunctionssim
(img1, img2)
experiments/ldm/ldm/modules/image_degradation/utils_image.py:669
↓ 3 callersMethodto_rgb
(self, x)
experiments/ldm/ldm/models/diffusion/ddpm.py:1386
↓ 2 callersFunctionNormalize
(in_channels)
experiments/ldm/ldm/modules/attention.py:76
↓ 2 callersMethod__init__
(self, batch_frequency, max_images, clamp=True, increase_log_steps=True, rescale=True, disabl
experiments/ldm/main.py:290
↓ 2 callersMethod__repr__
(self)
experiments/ddpm/ddpm/datasets/vision.py:34
↓ 2 callersMethod_check_integrity
(self)
experiments/ddpm/ddpm/datasets/celeba.py:108
↓ 2 callersFunction_filter2d
(input, kernel)
DeepCache/svd/pipeline_stable_video_diffusion.py:607
↓ 2 callersMethod_format_transform_repr
(self, transform, head)
experiments/ddpm/ddpm/datasets/vision.py:49
↓ 2 callersMethod_format_transform_repr
(self, transform, head)
experiments/ddpm/ddpm/datasets/vision.py:70
↓ 2 callersFunction_gaussian
(window_size: int, sigma)
DeepCache/svd/pipeline_stable_video_diffusion.py:630
↓ 2 callersMethod_get_add_time_ids
(self, original_size, crops_coords_top_left, target_size, dtype)
DeepCache/sdxl/pipeline_stable_diffusion_xl.py:519
↓ 2 callersMethod_get_denoise_row_from_list
(self, samples, desc='', force_no_decoder_quantization=False)
experiments/ldm/ldm/models/diffusion/ddpm.py:530
↓ 2 callersFunction_get_pipeline_class
( class_obj, config, load_connected_pipeline=False, custom_pipeline=None, cache_dir=None, revision=None )
DeepCache/sdxl/pipeline_utils.py:327
↓ 2 callersFunction_get_pipeline_class
( class_obj, config, load_connected_pipeline=False, custom_pipeline=None, repo_id=None,
DeepCache/svd/pipeline_utils.py:349
↓ 2 callersFunction_get_pipeline_class
( class_obj, config, load_connected_pipeline=False, custom_pipeline=None, cache_dir=None, revision=None )
DeepCache/sd/pipeline_utils.py:328
↓ 2 callersMethod_get_rows_from_list
(self, samples)
experiments/ldm/ldm/models/diffusion/ddpm.py:370
↓ 2 callersMethod_to_3d
(self, hidden_states, height, weight)
DeepCache/sdxl/unet_2d_blocks.py:3252
↓ 2 callersMethod_to_3d
(self, hidden_states, height, weight)
DeepCache/sd/unet_2d_blocks.py:3245
↓ 2 callersMethod_to_4d
(self, hidden_states, height, weight)
DeepCache/sdxl/unet_2d_blocks.py:3255
↓ 2 callersMethod_to_4d
(self, hidden_states, height, weight)
DeepCache/sd/unet_2d_blocks.py:3248
↓ 2 callersMethod_validation_step
(self, batch, batch_idx, suffix="")
experiments/ldm/ldm/models/autoencoder.py:170
↓ 2 callersFunctionadd_Gaussian_noise
(img, noise_level1=2, noise_level2=25)
experiments/ldm/ldm/modules/image_degradation/bsrgan_light.py:373
↓ 2 callersFunctionadd_Poisson_noise
(img)
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:404
↓ 2 callersFunctionadd_resize
(img, sf=4)
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:339
↓ 2 callersFunctionadd_speckle_noise
(img, noise_level1=2, noise_level2=25)
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:386
↓ 2 callersFunctionalways
(val)
experiments/ldm/ldm/modules/x_transformer.py:64
↓ 2 callersMethodbackward
(ctx, *output_grads)
experiments/ldm/ldm/modules/diffusionmodules/util.py:131
↓ 2 callersFunctionbicubic_degradation
Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image
experiments/ldm/ldm/modules/image_degradation/bsrgan_light.py:228
↓ 2 callersFunctionbicubic_degradation
Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:228
↓ 2 callersMethodcheck_inputs
( self, prompt, height, width, callback_steps, negative_prompt
DeepCache/sd/pipeline_stable_diffusion.py:498
↓ 2 callersMethodcopy_to
(self, model)
experiments/ldm/ldm/modules/ema.py:46
↓ 2 callersFunctioncount_flops_attn
A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr
experiments/ldm/ldm/modules/diffusionmodules/openaimodel.py:327
↓ 2 callersFunctioncubic
(x)
experiments/ldm/ldm/modules/image_degradation/utils_image.py:700
↓ 2 callersFunctioncustom_to_np
(x)
experiments/ldm/scripts/sample_diffusion.py:27
↓ 2 callersFunctionddpm_steps
(x, seq, model, b, **kwargs)
experiments/ddpm/ddpm/functions/denoising.py:35
↓ 2 callersMethoddecode
(self, z)
experiments/ldm/ldm/models/autoencoder.py:330
↓ 2 callersMethoddelta_border
:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and
experiments/ldm/ldm/models/diffusion/ddpm.py:571
↓ 2 callersMethoddisable
(self)
DeepCache/extension/deepcache.py:10
↓ 2 callersFunctiondownload_url
Download a file from a url and place it in root. Args: url (str): URL to download file from root (str): Directory to place downlo
experiments/ddpm/ddpm/datasets/utils.py:49
↓ 2 callersMethodenable_sequential_cpu_offload
r""" Offloads all models to CPU using 🤗 Accelerate, significantly reducing memory usage. When called, the state dicts of all `torch.nn
DeepCache/sdxl/pipeline_utils.py:1297
↓ 2 callersMethodencode_first_stage
(self, x)
experiments/ldm/ldm/models/diffusion/ddpm.py:826
↓ 2 callersMethodencode_prompt
r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):
DeepCache/sd/pipeline_stable_diffusion.py:297
↓ 2 callersFunctionexists
(x)
experiments/ldm/ldm/util.py:53
↓ 2 callersMethodfind_in_interval
(self, n)
experiments/ldm/ldm/lr_scheduler.py:52
↓ 2 callersFunctiongen_bar_updater
()
experiments/ddpm/ddpm/datasets/utils.py:8
↓ 2 callersFunctiongeneralized_steps
(x, seq, model, b, **kwargs)
experiments/ddpm/ddpm/functions/denoising.py:10
↓ 2 callersMethodget_conditioning
(self, batch, k=None)
experiments/ldm/ldm/models/diffusion/classifier.py:133
↓ 2 callersMethodget_first_stage_encoding
(self, encoder_posterior)
experiments/ldm/ldm/models/diffusion/ddpm.py:542
↓ 2 callersMethodget_input
(self, batch, k)
experiments/ldm/ldm/models/diffusion/classifier.py:124
↓ 2 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, cond_key=None, retu
experiments/ldm/ldm/models/diffusion/ddpm.py:654
↓ 2 callersFunctiongroup_dict_by_key
(cond, d)
experiments/ldm/ldm/modules/x_transformer.py:93
↓ 2 callersFunctiongroupby_prefix_and_trim
(prefix, d)
experiments/ldm/ldm/modules/x_transformer.py:110
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
experiments/ldm/ldm/models/diffusion/ddpm.py:186
↓ 2 callersFunctionis_safetensors_compatible
Checking for safetensors compatibility: - By default, all models are saved with the default pytorch serialization, so we use the list of defa
DeepCache/sdxl/pipeline_utils.py:138
↓ 2 callersFunctionis_safetensors_compatible
Checking for safetensors compatibility: - By default, all models are saved with the default pytorch serialization, so we use the list of defa
DeepCache/svd/pipeline_utils.py:137
↓ 2 callersFunctionis_safetensors_compatible
Checking for safetensors compatibility: - By default, all models are saved with the default pytorch serialization, so we use the list of defa
DeepCache/sd/pipeline_utils.py:138
↓ 2 callersMethodlog_img
(self, pl_module, batch, batch_idx, split="train")
experiments/ldm/main.py:340
↓ 2 callersFunctionmake_ddim_sampling_parameters
(alphacums, ddim_timesteps, eta, verbose=True)
experiments/ldm/ldm/modules/diffusionmodules/util.py:63
↓ 2 callersFunctionmake_ddim_timesteps
(ddim_discr_method, num_ddim_timesteps, num_ddpm_timesteps, verbose=True)
experiments/ldm/ldm/modules/diffusionmodules/util.py:46
↓ 2 callersFunctionmakedir_exist_ok
Python2 support for os.makedirs(.., exist_ok=True)
experiments/ddpm/ddpm/datasets/utils.py:36
↓ 2 callersMethodmaybe_free_model_hooks
r""" TODO: Better doc string
DeepCache/sdxl/pipeline_utils.py:1281
↓ 2 callersMethodmaybe_free_model_hooks
r""" TODO: Better doc string
DeepCache/sd/pipeline_utils.py:1281
↓ 2 callersFunctionmd5_hash
(path)
experiments/ddpm/ddpm/functions/ckpt_util.py:49
↓ 2 callersFunctionmkdir
(path)
experiments/ldm/ldm/modules/image_degradation/utils_image.py:153
↓ 2 callersMethodp_sample
(self, x, c, t, clip_denoised=False, repeat_noise=False, return_codebook_ids=False, quantize_
experiments/ldm/ldm/models/diffusion/ddpm.py:1079
↓ 2 callersMethodp_sample_loop
(self, shape, return_intermediates=False)
experiments/ldm/ldm/models/diffusion/ddpm.py:253
↓ 2 callersFunctionparallel_data_prefetch
( func: callable, data, n_proc, target_data_type="ndarray", cpu_intensive=True, use_worker_id=False )
experiments/ldm/ldm/util.py:108
↓ 2 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
experiments/ldm/ldm/models/diffusion/ddpm.py:216
↓ 2 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
DeepCache/sd/pipeline_stable_diffusion.py:481
↓ 2 callersMethodprepare_latents
(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None)
DeepCache/sd/pipeline_stable_diffusion.py:545
↓ 2 callersMethodprogress_bar
(self, iterable=None, total=None)
DeepCache/sdxl/pipeline_utils.py:1704
↓ 2 callersMethodprogress_bar
(self, iterable=None, total=None)
DeepCache/sd/pipeline_utils.py:1704
↓ 2 callersMethodprogressive_denoising
(self, cond, shape, verbose=True, callback=None, quantize_denoised=False, img_ca
experiments/ldm/ldm/models/diffusion/ddpm.py:1110
↓ 2 callersMethodq_posterior
(self, x_start, x_t, t)
experiments/ldm/ldm/models/diffusion/ddpm.py:222
↓ 2 callersFunctionrandom_crop
(lq, hq, sf=4, lq_patchsize=64)
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:427
↓ 2 callersMethodregister_modules
(self, **kwargs)
DeepCache/sdxl/pipeline_utils.py:506
↓ 2 callersMethodregister_schedule
(self, given_betas=None, beta_schedule="linear", timesteps=1000, linear_start=1e-4,
experiments/ldm/ldm/models/diffusion/ddpm.py:117
↓ 2 callersMethodreset_states
(self)
DeepCache/extension/deepcache.py:109
↓ 2 callersMethodrestore
Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the
experiments/ldm/ldm/modules/ema.py:64
↓ 2 callersFunctionrnn_flops
(flops, rnn_module, w_ih, w_hh, input_size)
DeepCache/flops.py:130
← previousnext →101–200 of 1,211, ranked by callers