MCPcopy Create free account

hub / github.com/AlayaLab/AlayaRenderer / functions

Functions1,613 in github.com/AlayaLab/AlayaRenderer

⨍ Functions 1,613◇ Types & classes 459↳ Endpoints 1
↓ 436 callersMethodto
(self, *args, **kwargs)
game_editing/diffsynth/diffusion/base_pipeline.py:87
↓ 78 callersMethodload_models_to_device
(self, model_names)
game_editing/diffsynth/diffusion/base_pipeline.py:148
↓ 56 callersMethodfetch_model
(self, model_name, index=None)
game_editing/diffsynth/models/model_loader.py:83
↓ 49 callersMethodclone
(self)
game_editing/diffsynth/models/ltx2_common.py:176
↓ 42 callersMethodupdate
(self, hidden_states)
game_editing/diffsynth/pipelines/wan_video.py:1068
↓ 40 callersMethodencode
Encode a batch of images into latents. Args: x (`torch.Tensor`): Input batch of images. return_dict (`bool`,
game_editing/diffsynth/models/flux2_vae.py:2057
↓ 40 callersMethodpreprocess_image
(self, image, torch_dtype=None, device=None, pattern="B C H W", min_value=-1, max_value=1)
game_editing/diffsynth/diffusion/base_pipeline.py:114
↓ 37 callersFunctionget_device_type
Get device type based on current machine, currently only support CPU, CUDA, NPU.
game_editing/diffsynth/core/device/npu_compatible_device.py:19
↓ 27 callersMethodnorm
(self, x)
game_editing/diffsynth/models/wan_video_dit.py:107
↓ 26 callersMethodkeys
(self)
game_editing/diffsynth/core/vram/disk_map.py:18
↓ 24 callersMethod__init__
(self, num_inference_steps, rel_l1_thresh, model_id)
game_editing/diffsynth/pipelines/wan_video.py:1022
↓ 23 callersMethodempty
()
game_editing/diffsynth/models/ltx2_dit.py:192
↓ 20 callersMethod__init__
(self, num_inference_steps, rel_l1_thresh)
game_editing/diffsynth/pipelines/flux_image.py:909
↓ 19 callersMethodto
(self,device)
game_editing/diffsynth/utils/controlnet/annotator.py:43
↓ 17 callersMethod__init__
( self, in_channels: int, out_channels: int, factor_t, factor_s=1,
game_editing/diffsynth/models/wan_video_vae.py:399
↓ 17 callersMethod__init__
(self, kernel, pad, upsample_factor=1)
game_editing/diffsynth/models/wan_video_animate_adapter.py:370
↓ 17 callersMethodpreprocess_video
(self, video, torch_dtype=None, device=None, pattern="B C T H W", min_value=-1, max_value=1)
game_editing/diffsynth/diffusion/base_pipeline.py:123
↓ 15 callersMethoddownload_if_necessary
(self)
game_editing/diffsynth/core/loader/config.py:96
↓ 15 callersFunctiongradient_checkpoint_forward
( model, use_gradient_checkpointing, use_gradient_checkpointing_offload, *args, **kwargs,
game_editing/diffsynth/core/gradient/gradient_checkpoint.py:10
↓ 15 callersMethodstep
(self, scheduler, latents, progress_id, noise_pred, input_latents=None, inpaint_mask=None, **kwargs)
game_editing/diffsynth/diffusion/base_pipeline.py:211
↓ 14 callersFunctioncreate_custom_forward
(module)
game_editing/diffsynth/pipelines/wan_video.py:1324
↓ 14 callersMethodset_timesteps
(self, num_inference_steps=100, denoising_strength=1.0, training=False, **kwargs)
game_editing/diffsynth/diffusion/flow_match.py:189
↓ 13 callersMethod__init__
(self, device=get_device_type(), torch_dtype=torch.bfloat16)
game_editing/diffsynth/pipelines/qwen_image.py:26
↓ 12 callersMethod__init__
( self, patch_size: int = 1, in_channels: int = 128, out_channels: Optional[in
game_editing/diffsynth/models/flux2_dit.py:880
↓ 12 callersFunctionmake_conv_nd
( # noqa: PLR0913 dims: Union[int, Tuple[int, int]], in_channels: int, out_channels: int, ker
game_editing/diffsynth/models/ltx2_video_vae.py:412
↓ 12 callersMethodpatchify
(self, hidden_states)
game_editing/diffsynth/models/flux_dit.py:296
↓ 12 callersMethodrope_params
Args: index: [0, 1, 2, 3] 1D Tensor representing the position index of the token
game_editing/diffsynth/models/qwen_image_dit.py:80
↓ 11 callersMethod__init__
(self, embed_dim=512, image_size=224, patch_size=16,
game_editing/diffsynth/models/wan_video_image_encoder.py:483
↓ 11 callersMethod__init__
( self, dim: int, num_heads: int, enable_flashattn3: bool = False, ena
game_editing/diffsynth/models/longcat_video_dit.py:139
↓ 11 callersFunctionrms_norm
Root-mean-square (RMS) normalize `x` over its last dimension. Thin wrapper around `torch.nn.functional.rms_norm` that infers the normalized sh
game_editing/diffsynth/models/ltx2_common.py:240
↓ 10 callersMethod__init__
(self, device=get_device_type(), torch_dtype=torch.bfloat16)
game_editing/diffsynth/pipelines/z_image.py:29
↓ 10 callersMethod__init__
( self, in_channels: int, with_conv: bool, causality_axis: CausalityAxis = Cau
game_editing/diffsynth/models/ltx2_audio_vae.py:661
↓ 10 callersMethodfrom_pretrained
( torch_dtype: torch.dtype = torch.bfloat16, device: Union[str, torch.device] = get_device_typ
game_editing/diffsynth/pipelines/z_image.py:60
↓ 9 callersMethod__init__
( # noqa: PLR0913 self, *, model_type: LTXModelType = LTXModelType.AudioVideo,
game_editing/diffsynth/models/ltx2_dit.py:1071
↓ 9 callersMethod__init__
( self, in_channels: int = 3, out_channels: int = 3, down_block_types: Tuple[s
game_editing/diffsynth/models/flux2_vae.py:1650
↓ 9 callersMethod__init__
( self, base_dim: int = 96, z_dim: int = 16, dim_mult: Tuple[int] = [1, 2, 4,
game_editing/diffsynth/models/qwen_image_vae.py:643
↓ 9 callersMethodcfg_guided_model_fn
(self, model_fn, cfg_scale, inputs_shared, inputs_posi, inputs_nega, **inputs_others)
game_editing/diffsynth/diffusion/base_pipeline.py:312
↓ 9 callersMethodcreate_coordinate_grid
(size, start=None, device=None)
game_editing/diffsynth/models/z_image_dit.py:503
↓ 9 callersMethodload
(self, model: torch.nn.Module, state_dict_lora, alpha=1.0)
game_editing/diffsynth/models/flux_lora_patcher.py:123
↓ 9 callersFunctionmake_conv2d
Create a 2D convolution layer that can be either causal or non-causal. Args: in_channels: Number of input channels out_channe
game_editing/diffsynth/models/ltx2_audio_vae.py:341
↓ 8 callersMethod__init__
( self, in_channels, hidden_channels=None, out_features=None, act_laye
game_editing/diffsynth/models/step1x_connector.py:25
↓ 8 callersMethod__init__
(self, in_dim, out_dim, has_pos_emb=False)
game_editing/diffsynth/models/wan_video_dit.py:235
↓ 8 callersMethod__init__
( self, in_channels: int, out_channels: int, kernel_size: int, stride:
game_editing/diffsynth/models/ltx2_video_vae.py:183
↓ 8 callersMethodgenerate_noise
(self, shape, seed=None, rand_device="cpu", rand_torch_dtype=torch.float32, device=None, torch_dtype=None)
game_editing/diffsynth/diffusion/base_pipeline.py:173
↓ 8 callersMethodis_audio_enabled
(self)
game_editing/diffsynth/models/ltx2_dit.py:1061
↓ 8 callersMethodis_video_enabled
(self)
game_editing/diffsynth/models/ltx2_dit.py:1058
↓ 8 callersMethodprepare
( self, modality: Modality, )
game_editing/diffsynth/models/ltx2_dit.py:652
↓ 8 callersMethodupdate
(self, hidden_states)
game_editing/diffsynth/pipelines/flux_image.py:946
↓ 7 callersMethod__init__
(self, device=get_device_type(), torch_dtype=torch.bfloat16)
game_editing/diffsynth/pipelines/flux2_image.py:23
↓ 7 callersMethod__init__
(self, q_dim, num_heads, head_dim, kv_dim=None, bias_q=False, bias_kv=False, bias_out=False)
game_editing/diffsynth/models/flux_vae.py:155
↓ 7 callersMethod__init__
(self, disable_guidance_embedder=False, input_dim=64, num_blocks=19)
game_editing/diffsynth/models/flux_dit.py:278
↓ 7 callersMethodafter_transformer_block
(self, block_idx, hidden_states, audio_emb_global, audio_emb, original_seq_len, use_unified_sequence_parallel=
game_editing/diffsynth/models/wan_video_dit_s2v.py:459
↓ 7 callersFunctioncheck_is_instance
(model, module_class)
game_editing/diffsynth/models/wan_video_vae.py:11
↓ 7 callersMethoddecode
( self, z: torch.FloatTensor, return_dict: bool = True, generator=None )
game_editing/diffsynth/models/flux2_vae.py:2102
↓ 7 callersFunctionflash_attention
(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, num_heads: int, compatibility_mode=False)
game_editing/diffsynth/models/wan_video_dit.py:28
↓ 7 callersFunctionmodulate
(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor)
game_editing/diffsynth/models/wan_video_dit.py:64
↓ 7 callersMethodset_processor
r""" Set the attention processor to use. Args: processor (`AttnProcessor`): The attention processor to us
game_editing/diffsynth/models/flux2_vae.py:917
↓ 7 callersFunctionsinusoidal_embedding_1d
(dim, position)
game_editing/diffsynth/models/wan_video_dit.py:68
↓ 6 callersMethod__init__
(self, device=get_device_type(), torch_dtype=torch.bfloat16)
game_editing/diffsynth/pipelines/ltx2_audio_video.py:29
↓ 6 callersMethod__init__
(self, config)
game_editing/diffsynth/models/nexus_gen_projector.py:182
↓ 6 callersMethod__init__
( self, dim: int, in_dim: int, ffn_dim: int, out_dim: int, tex
game_editing/diffsynth/models/wan_video_dit_s2v.py:361
↓ 6 callersMethod__init__
( self, num_layers: int = 60, use_layer3d_rope: bool = False, use_additional_t
game_editing/diffsynth/models/qwen_image_dit.py:552
↓ 6 callersMethodadd_noise
(self, original_samples, noise, timestep)
game_editing/diffsynth/diffusion/flow_match.py:221
↓ 6 callersMethodcheck_resize_height_width
(self, height, width, num_frames=None)
game_editing/diffsynth/diffusion/base_pipeline.py:97
↓ 6 callersMethodcheck_vram_management_state
(self)
game_editing/diffsynth/diffusion/base_pipeline.py:304
↓ 6 callersMethodclear_cache
(self)
game_editing/diffsynth/models/wan_video_vae.py:1048
↓ 6 callersMethoddownload_and_load_models
(self, model_configs: list[ModelConfig] = [], vram_limit: float = None)
game_editing/diffsynth/diffusion/base_pipeline.py:287
↓ 6 callersMethodget_ada_values
( self, scale_shift_table: torch.Tensor, batch_size: int, timestep: torch.Tensor, indices: slice )
game_editing/diffsynth/models/ltx2_dit.py:861
↓ 6 callersFunctionget_torch_device
Get torch attribute based on device type, e.g. torch.cuda or torch.npu
game_editing/diffsynth/core/device/npu_compatible_device.py:31
↓ 6 callersFunctionrope_apply
(x, freqs, num_heads)
game_editing/diffsynth/models/wan_video_dit.py:92
↓ 6 callersMethodrope_params
Args: index: [0, 1, 2, 3] 1D Tensor representing the position index of the token
game_editing/diffsynth/models/qwen_image_dit.py:254
↓ 6 callersMethodvae_output_to_image
(self, vae_output, pattern="B C H W", min_value=-1, max_value=1)
game_editing/diffsynth/diffusion/base_pipeline.py:130
↓ 5 callersMethod__init__
(self, dim, eps=1e-6)
game_editing/diffsynth/models/wan_video_text_encoder.py:27
↓ 5 callersMethod__init__
(self, q_dim, num_heads, head_dim, kv_dim=None, bias_q=False, bias_kv=False, bias_out=False)
game_editing/diffsynth/models/flux_lora_encoder.py:17
↓ 5 callersMethod__init__
(self, q_dim, num_heads, head_dim, kv_dim=None, bias_q=False, bias_kv=False, bias_out=False)
game_editing/diffsynth/models/z_image_dit.py:76
↓ 5 callersFunctionbuild_normalization_layer
Create a normalization layer based on the normalization type. Args: in_channels: Number of input channels num_groups: Number
game_editing/diffsynth/models/ltx2_common.py:221
↓ 5 callersMethodencode_image
(self, videos)
game_editing/diffsynth/models/wan_video_image_encoder.py:864
↓ 5 callersMethodimport_model_class
(self, model_class)
game_editing/diffsynth/models/model_loader.py:13
↓ 5 callersFunctionload_state_dict
(file_path, torch_dtype=None, device="cpu", pin_memory=False, verbose=0)
game_editing/diffsynth/core/loader/file.py:5
↓ 5 callersMethodnormalize
(self, x: torch.Tensor)
game_editing/diffsynth/models/ltx2_audio_vae.py:771
↓ 5 callersFunctionprecompute_freqs_cis
( indices_grid: torch.Tensor, dim: int, out_dtype: torch.dtype, theta: float = 10000.0, ma
game_editing/diffsynth/models/ltx2_dit.py:424
↓ 5 callersFunctionrearrange_out
(out: torch.Tensor, out_pattern="b n s d", required_out_pattern="b n s d", dims=None)
game_editing/diffsynth/core/attention/attention.py:59
↓ 5 callersFunctionrearrange_qkv
(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s
game_editing/diffsynth/core/attention/attention.py:48
↓ 5 callersFunctionselect_per_token
( value_noisy: torch.Tensor, value_clean: torch.Tensor, noise_mask: torch.Tensor, seq_len: int
game_editing/diffsynth/models/z_image_dit.py:142
↓ 5 callersMethodunpatchify
(self, hidden_states, height, width)
game_editing/diffsynth/models/flux_dit.py:301
↓ 4 callersMethod__init__
(self, channels: int, mid_channels: Optional[int] = None, dims: int = 3)
game_editing/diffsynth/models/ltx2_upsampler.py:70
↓ 4 callersMethod__init__
(self, dim, eps, elementwise_affine=True)
game_editing/diffsynth/models/general_modules.py:105
↓ 4 callersMethod__init__
(self)
game_editing/diffsynth/models/ltx2_text_encoder.py:9
↓ 4 callersMethod__init__
(self, lora_patterns, in_dim=1536+4096, compress_dim=128, rank=4, block_id=0, use_residual=True, residual_leng
game_editing/diffsynth/models/z_image_image2lora.py:6
↓ 4 callersMethod__init__
(self, in_dim, mid_dim, out_dim, bias=False)
game_editing/diffsynth/models/qwen_image_image2lora.py:5
↓ 4 callersMethod_modulate
(self, x, mod_params, index=None)
game_editing/diffsynth/models/qwen_image_dit.py:470
↓ 4 callersMethod_process_attn
(self, q, k, v, shape)
game_editing/diffsynth/models/longcat_video_dit.py:173
↓ 4 callersFunctionapply_rotary_emb
( input_tensor: torch.Tensor, freqs_cis: Tuple[torch.Tensor, torch.Tensor], rope_type: LTXRopeType
game_editing/diffsynth/models/ltx2_dit.py:261
↓ 4 callersFunctionapply_rotary_emb
Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query or key
game_editing/diffsynth/models/flux2_dit.py:241
↓ 4 callersFunctionapply_rotary_emb_qwen
( x: torch.Tensor, freqs_cis: Union[torch.Tensor, Tuple[torch.Tensor]] )
game_editing/diffsynth/models/qwen_image_dit.py:51
↓ 4 callersFunctionattention_forward
(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s
game_editing/diffsynth/core/attention/attention.py:108
↓ 4 callersMethodencode
(self, x, scale)
game_editing/diffsynth/models/wan_video_vae.py:984
↓ 4 callersMethodis_perturbed
(self, perturbation_type: PerturbationType, block: int)
game_editing/diffsynth/models/ltx2_dit.py:169
↓ 4 callersMethodmask_like
(self, perturbation_type: PerturbationType, block: int, values: torch.Tensor)
game_editing/diffsynth/models/ltx2_dit.py:212
↓ 4 callersFunctionparse_device_type
(device)
game_editing/diffsynth/core/device/npu_compatible_device.py:85
next →1–100 of 1,613, ranked by callers