MCPcopy Create free account

hub / github.com/horseee/DeepCache / functions

Functions1,211 in github.com/horseee/DeepCache

⨍ Functions 1,211◇ Types & classes 220
Methodcustom_forward
(*inputs)
DeepCache/svd/unet_3d_blocks.py:1709
Methodcustom_forward
(*inputs)
DeepCache/svd/unet_3d_blocks.py:1941
Methodcustom_forward
(*inputs)
DeepCache/svd/unet_3d_blocks.py:2032
Methodcustom_forward
(*inputs)
DeepCache/svd/unet_3d_blocks.py:2149
Methodcustom_forward
(*inputs)
DeepCache/svd/unet_3d_blocks.py:2258
Methodcustom_forward
(*inputs)
DeepCache/svd/unet_3d_blocks.py:2373
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:678
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:1067
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:1177
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:1602
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:1753
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:1842
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:1948
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:2220
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:2320
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:2772
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:2927
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:3016
Methodcustom_forward
(*inputs)
DeepCache/sd/unet_2d_blocks.py:3143
Functionddpm_steps
(x, seq, model, b, **kwargs)
experiments/ddpm/ddpm/functions/deepcache_denoising.py:104
Methoddecode
(self, text)
experiments/ldm/ldm/modules/encoders/modules.py:76
Methoddecode
(self, h, force_not_quantize=False)
experiments/ldm/ldm/models/autoencoder.py:274
Methoddecode
(self, x, *args, **kwargs)
experiments/ldm/ldm/models/autoencoder.py:434
Methoddecode_code
(self, code_b)
experiments/ldm/ldm/models/autoencoder.py:112
Functiondegradation_bsrgan
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
experiments/ldm/ldm/modules/image_degradation/bsrgan_light.py:442
Functiondegradation_bsrgan
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:438
Functiondegradation_bsrgan_plus
This is an extended degradation model by combining the degradation models of BSRGAN and Real-ESRGAN ---------- img: HXWXC, [0, 1], it
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:617
Functiondegradation_bsrgan_variant
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
experiments/ldm/ldm/modules/image_degradation/bsrgan_light.py:534
Functiondegradation_bsrgan_variant
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:530
Methoddenoising_value_valid
(dnv)
DeepCache/sdxl/pipeline_stable_diffusion_xl_img2img.py:905
Methoddifferentiable_decode_first_stage
(self, z, predict_cids=False, force_not_quantize=False)
experiments/ldm/ldm/models/diffusion/ddpm.py:766
Methoddisable_attention_slicing
r""" Disable sliced attention computation. If `enable_attention_slicing` was previously called, attention is computed in one step.
DeepCache/sdxl/pipeline_utils.py:1823
Methoddisable_attention_slicing
r""" Disable sliced attention computation. If `enable_attention_slicing` was previously called, attention is computed in one step.
DeepCache/svd/pipeline_utils.py:2090
Methoddisable_attention_slicing
r""" Disable sliced attention computation. If `enable_attention_slicing` was previously called, attention is computed in one step.
DeepCache/sd/pipeline_utils.py:1823
Methoddisable_vae_slicing
r""" Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to computing decoding in on
DeepCache/sdxl/pipeline_stable_diffusion_xl.py:191
Methoddisable_vae_slicing
r""" Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to computing decoding in on
DeepCache/sdxl/pipeline_stable_diffusion_xl_img2img.py:198
Methoddisable_vae_slicing
r""" Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to computing decoding in on
DeepCache/sd/pipeline_stable_diffusion.py:245
Methoddisable_vae_tiling
r""" Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to computing decoding in one
DeepCache/sdxl/pipeline_stable_diffusion_xl.py:208
Methoddisable_vae_tiling
r""" Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to computing decoding in one
DeepCache/sdxl/pipeline_stable_diffusion_xl_img2img.py:215
Methoddisable_vae_tiling
r""" Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to computing decoding in one
DeepCache/sd/pipeline_stable_diffusion.py:260
Methoddisable_xformers_memory_efficient_attention
r""" Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).
DeepCache/sdxl/pipeline_utils.py:1757
Methoddisable_xformers_memory_efficient_attention
r""" Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).
DeepCache/svd/pipeline_utils.py:2024
Methoddisable_xformers_memory_efficient_attention
r""" Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).
DeepCache/sd/pipeline_utils.py:1757
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
experiments/ldm/ldm/models/diffusion/classifier.py:22
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
experiments/ldm/ldm/models/diffusion/ddpm.py:34
Functiondivein
(*args, **kwargs)
experiments/ldm/main.py:705
Methoddo_classifier_free_guidance
(self)
DeepCache/svd/pipeline_stable_video_diffusion.py:291
Functiondpsr_degradation
bicubic downsampling + blur Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam
experiments/ldm/ldm/modules/image_degradation/bsrgan_light.py:262
Functiondpsr_degradation
bicubic downsampling + blur Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam
experiments/ldm/ldm/modules/image_degradation/bsrgan.py:262
Methoddtype
r""" Returns: `torch.dtype`: The torch dtype on which the pipeline is located.
DeepCache/svd/pipeline_utils.py:900
Functionempty_flops_counter_hook
(module, input, output)
DeepCache/flops.py:53
Methodenable_forward_chunking
Sets the attention processor to use [feed forward chunking](https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers).
DeepCache/svd/unet_spatio_temporal_condition.py:328
Methodenable_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/svd/pipeline_utils.py:1481
Methodenable_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/sd/pipeline_utils.py:1297
Methodenable_vae_slicing
r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev
DeepCache/sdxl/pipeline_stable_diffusion_xl.py:183
Methodenable_vae_slicing
r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev
DeepCache/sdxl/pipeline_stable_diffusion_xl_img2img.py:190
Methodenable_vae_slicing
r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev
DeepCache/sd/pipeline_stable_diffusion.py:238
Methodenable_vae_tiling
r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en
DeepCache/sdxl/pipeline_stable_diffusion_xl.py:199
Methodenable_vae_tiling
r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en
DeepCache/sdxl/pipeline_stable_diffusion_xl_img2img.py:206
Methodenable_vae_tiling
r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en
DeepCache/sd/pipeline_stable_diffusion.py:252
Methodenable_xformers_memory_efficient_attention
r""" Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/). When this option is enabled, you
DeepCache/sdxl/pipeline_utils.py:1722
Methodenable_xformers_memory_efficient_attention
r""" Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/). When this option is enabled, you
DeepCache/svd/pipeline_utils.py:1989
Methodenable_xformers_memory_efficient_attention
r""" Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/). When this option is enabled, you
DeepCache/sd/pipeline_utils.py:1722
Methodencode
(self, *args, **kwargs)
experiments/ldm/ldm/modules/encoders/modules.py:16
Methodencode
(self, x)
experiments/ldm/ldm/modules/encoders/modules.py:49
Methodencode
(self, text)
experiments/ldm/ldm/modules/encoders/modules.py:70
Methodencode
(self, x)
experiments/ldm/ldm/modules/encoders/modules.py:134
Methodencode
(self, text)
experiments/ldm/ldm/modules/encoders/modules.py:162
Methodencode
(self, x)
experiments/ldm/ldm/models/autoencoder.py:269
Methodencode
(self, x, *args, **kwargs)
experiments/ldm/ldm/models/autoencoder.py:431
Methodencode_to_prequant
(self, x)
experiments/ldm/ldm/models/autoencoder.py:102
Methodextra_repr
(self)
experiments/ddpm/ddpm/datasets/lsun.py:174
Methodextra_repr
(self)
experiments/ddpm/ddpm/datasets/celeba.py:161
Methodfn_recursive_add_processors
(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor])
DeepCache/sdxl/unet_2d_condition.py:605
Methodfn_recursive_add_processors
( name: str, module: torch.nn.Module, processors: Dict[str, AttentionProce
DeepCache/svd/unet_spatio_temporal_condition.py:258
Methodfn_recursive_add_processors
(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor])
DeepCache/sd/unet_2d_condition.py:605
Methodfn_recursive_attn_processor
(name: str, module: torch.nn.Module, processor)
DeepCache/sdxl/unet_2d_condition.py:642
Methodfn_recursive_attn_processor
(name: str, module: torch.nn.Module, processor)
DeepCache/svd/unet_spatio_temporal_condition.py:297
Methodfn_recursive_attn_processor
(name: str, module: torch.nn.Module, processor)
DeepCache/sd/unet_2d_condition.py:642
Methodfn_recursive_feed_forward
(module: torch.nn.Module, chunk_size: int, dim: int)
DeepCache/svd/unet_spatio_temporal_condition.py:347
Methodfn_recursive_retrieve_sliceable_dims
(module: torch.nn.Module)
DeepCache/sdxl/unet_2d_condition.py:686
Methodfn_recursive_retrieve_sliceable_dims
(module: torch.nn.Module)
DeepCache/sd/unet_2d_condition.py:686
Methodfn_recursive_set_attention_slice
(module: torch.nn.Module, slice_size: List[int])
DeepCache/sdxl/unet_2d_condition.py:724
Methodfn_recursive_set_attention_slice
(module: torch.nn.Module, slice_size: List[int])
DeepCache/sd/unet_2d_condition.py:724
Methodfn_recursive_set_mem_eff
(module: torch.nn.Module)
DeepCache/sdxl/pipeline_utils.py:1769
Methodfn_recursive_set_mem_eff
(module: torch.nn.Module)
DeepCache/svd/pipeline_utils.py:2036
Methodfn_recursive_set_mem_eff
(module: torch.nn.Module)
DeepCache/sd/pipeline_utils.py:1769
Methodforward
r""" The [`UNet2DConditionModel`] forward method. Args: sample (`torch.FloatTensor`): The noisy input ten
DeepCache/sdxl/unet_2d_condition.py:739
Methodforward
(self, x)
DeepCache/sdxl/unet_2d_blocks.py:478
Methodforward
(self, hidden_states, temb=None)
DeepCache/sdxl/unet_2d_blocks.py:563
Methodforward
( self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None,
DeepCache/sdxl/unet_2d_blocks.py:663
Methodforward
( self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None,
DeepCache/sdxl/unet_2d_blocks.py:800
Methodforward
(self, hidden_states, temb=None, upsample_size=None, cross_attention_kwargs=None)
DeepCache/sdxl/unet_2d_blocks.py:931
Methodforward
( self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None,
DeepCache/sdxl/unet_2d_blocks.py:1046
Methodforward
(self, hidden_states, temb=None, scale: float = 1.0, exist_block_number=None,)
DeepCache/sdxl/unet_2d_blocks.py:1169
Methodforward
(self, hidden_states, scale: float = 1.0)
DeepCache/sdxl/unet_2d_blocks.py:1256
Methodforward
(self, hidden_states, scale: float = 1.0)
DeepCache/sdxl/unet_2d_blocks.py:1339
Methodforward
(self, hidden_states, temb=None, skip_sample=None, scale: float = 1.0)
DeepCache/sdxl/unet_2d_blocks.py:1433
Methodforward
(self, hidden_states, temb=None, skip_sample=None, scale: float = 1.0)
DeepCache/sdxl/unet_2d_blocks.py:1514
Methodforward
(self, hidden_states, temb=None, scale: float = 1.0)
DeepCache/sdxl/unet_2d_blocks.py:1597
← previousnext →801–900 of 1,211, ranked by callers