MCPcopy Create free account

hub / github.com/brycedrennan/imaginAIry / functions

Functions2,992 in github.com/brycedrennan/imaginAIry

⨍ Functions 2,992◇ Types & classes 731↳ Endpoints 37
↓ 2 callersFunctionimage_from_textimg_str
Create an image from a textimg string.
imaginairy/utils/text_image.py:89
↓ 2 callersFunctionimage_to_tensor
Converts a PIL image to a PyTorch tensor. Args: - image (PIL.Image): The image to convert. - device (torch.device): The device to us
imaginairy/enhancers/video_interpolation/rife/interpolate.py:393
↓ 2 callersFunctionimaginairy_click_context
(log_level="INFO")
imaginairy/cli/shared.py:15
↓ 2 callersMethodimportance
(self, crop, x, y)
imaginairy/vendored/smart_crop.py:313
↓ 2 callersFunctionimwrite
Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li
imaginairy/vendored/facexlib/utils/misc.py:11
↓ 2 callersFunctionindex_default
(items, index, default)
imaginairy/cli/imagine.py:238
↓ 2 callersMethodinit_context
(self)
imaginairy/vendored/refiners/fluxion/layers/chain.py:170
↓ 2 callersFunctioninit_detection_model
(model_name, half=False, device='cuda', model_rootpath=None)
imaginairy/vendored/facexlib/detection/__init__.py:8
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=(), only_model=False)
imaginairy/modules/diffusion/ddpm.py:418
↓ 2 callersMethodinit_from_state_dict
(self, sd, ignore_keys=(), only_model=False)
imaginairy/modules/diffusion/ddpm.py:325
↓ 2 callersMethodinitialize
(self, input_tensor)
imaginairy/modules/sgm/autoencoding/lpips/util.py:59
↓ 2 callersMethodinject
(self: "SD1T2IAdapter", parent: fl.Chain | None = None)
imaginairy/vendored/refiners/foundationals/latent_diffusion/stable_diffusion_1/t2i_adapter.py:26
↓ 2 callersMethodinstantiate_optimizer_from_config
(self, params, lr, cfg)
imaginairy/modules/sgm/autoencoder.py:104
↓ 2 callersFunctionis_blurry
(img, threshold=0.91)
imaginairy/enhancers/blur_detect.py:18
↓ 2 callersFunctionis_url
(url_or_filename)
imaginairy/vendored/blip/blip.py:271
↓ 2 callersFunctionisimage
(x)
imaginairy/modules/diffusion/ddpm.py:86
↓ 2 callersFunctionismap
(x)
imaginairy/modules/diffusion/ddpm.py:80
↓ 2 callersFunctionl2_norm
(input, axis=1)
imaginairy/vendored/facexlib/recognition/arcface_arch.py:15
↓ 2 callersFunctionload_midas_transform
(model_type="dpt_hybrid")
imaginairy/modules/midas/api.py:47
↓ 2 callersFunctionload_model
(device=None, sampling_ratio=0.4, importance_ratio=0.7)
imaginairy/vendored/imaginairy_normal_map/model.py:88
↓ 2 callersFunctionload_rife_model
(model_path=None, version=4.13, device=None)
imaginairy/enhancers/video_interpolation/rife/interpolate.py:82
↓ 2 callersFunctionload_sd15_diffusers_weights
(base_url: str, device=None)
imaginairy/utils/model_manager.py:496
↓ 2 callersFunctionload_stable_diffusion_compvis_weights
(weights_url)
imaginairy/utils/model_manager.py:715
↓ 2 callersMethodload_weights
(self, down_weight: Tensor, up_weight: Tensor)
imaginairy/vendored/refiners/fluxion/adapters/lora.py:90
↓ 2 callersMethodlog_progress_latent
(self, latent)
imaginairy/utils/log_utils.py:333
↓ 2 callersFunctionmake_animation
( imgs, outpath, frame_duration_ms: int | List[int] = 100, captions=None )
imaginairy/utils/animations.py:106
↓ 2 callersFunctionmake_backbone_default
( model, features=[96, 192, 384, 768], size=[384, 384], hooks=[2, 5, 8, 11], vit_features=
imaginairy/modules/midas/midas/backbones/utils.py:142
↓ 2 callersFunctionmake_beta_schedule
( schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3 )
imaginairy/modules/diffusion/util.py:25
↓ 2 callersFunctionmake_beta_schedule
( schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, )
imaginairy/modules/sgm/diffusionmodules/util.py:20
↓ 2 callersFunctionmake_clothing_segmentation_diagram
( image_pil, seg, color_seg, segment_names, palette: list )
imaginairy/img_processors/segformer_b2_clothes.py:174
↓ 2 callersFunctionmake_gif_animation
(imgs, outpath, frame_duration_ms=100, loop=0)
imaginairy/utils/animations.py:128
↓ 2 callersFunctionmake_inference
(I0, I1, n, *, model, scale)
imaginairy/enhancers/video_interpolation/rife/interpolate.py:94
↓ 2 callersFunctionmake_noise_disk
(H: int, W: int, C: int, F: int)
imaginairy/img_processors/control_modes.py:160
↓ 2 callersMethodmd5
(self)
imaginairy/schema.py:886
↓ 2 callersFunctionmd5_hash
(path)
imaginairy/modules/sgm/autoencoding/lpips/util.py:29
↓ 2 callersMethodmemory_allocated
(cls)
tests/test_utils/test_memory_tracker.py:20
↓ 2 callersMethodmerge_multi_head
( self, x: Float[Tensor, "batch_size num_heads sequence_length heads_dim"] )
imaginairy/vendored/refiners/fluxion/layers/attentions.py:115
↓ 2 callersMethodmeshgrid
(self, h, w)
imaginairy/modules/autoencoder.py:574
↓ 2 callersMethodmode
(self)
imaginairy/modules/distributions.py:55
↓ 2 callersMethodmode
(self)
imaginairy/modules/sgm/distributions/distributions.py:22
↓ 2 callersFunctionmodel_latent_to_pillow_img
(latent: torch.Tensor)
imaginairy/utils/img_utils.py:126
↓ 2 callersFunctionmove_roi_into_bounds
Move a region of interest into the bounds of the image.
imaginairy/utils/roi_utils.py:75
↓ 2 callersMethodmove_to_end
(self, key, last=True)
imaginairy/utils/model_cache.py:69
↓ 2 callersFunctionnormalize
( tensor: Float[Tensor, "*batch channels height width"], mean: list[float], std: list[float] )
imaginairy/vendored/refiners/fluxion/utils.py:50
↓ 2 callersFunctionnormalize_diffusers_repo_url
(url: str)
imaginairy/utils/downloads.py:218
↓ 2 callersFunctionnormalize_tensor
(x, eps=1e-10)
imaginairy/modules/sgm/autoencoding/lpips/loss/lpips.py:145
↓ 2 callersFunctionorthogonal_
(module)
imaginairy/vendored/k_diffusion/models/image_v1.py:8
↓ 2 callersFunctionoutpaint_calculations
( img_width, img_height, up=None, down=None, left=None, right=None, _all=0, sn
imaginairy/utils/outpaint.py:12
↓ 2 callersFunctionpad64
(x)
imaginairy/img_processors/densepose.py:30
↓ 2 callersFunctionparse_schedule_str
Parse a schedule string into a list of values.
imaginairy/utils/prompt_schedules.py:11
↓ 2 callersFunctionpatch_device
(module)
imaginairy/vendored/clip/clip.py:187
↓ 2 callersFunctionpatch_float
(module)
imaginairy/vendored/clip/clip.py:215
↓ 2 callersFunctionpillow_img_to_opencv_img
(img: PIL.Image.Image | LazyLoadingImage)
imaginairy/utils/img_utils.py:83
↓ 2 callersFunctionpillow_mask_to_latent_mask
( mask_img: PIL.Image.Image | LazyLoadingImage, downsampling_factor )
imaginairy/utils/img_utils.py:66
↓ 2 callersFunctionpixel_unshuffle
Pixel unshuffle. Args: x (Tensor): Input feature with shape (b, c, hh, hw). scale (int): Downsample ratio. Returns:
imaginairy/vendored/basicsr/arch_util.py:63
↓ 2 callersMethodpost_process
(self)
imaginairy/vendored/realesrgan.py:206
↓ 2 callersMethodpre_process
Pre-process, such as pre-pad and mod pad, so that the images can be divisible.
imaginairy/vendored/realesrgan.py:106
↓ 2 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
imaginairy/modules/diffusion/ddpm.py:436
↓ 2 callersFunctionprep_control_input
( control_input: ControlInput, sd, init_image_t, fit_width, fit_height )
imaginairy/api/generate_refiners.py:467
↓ 2 callersFunctionprepare_image_for_outpaint
( img, mask=None, up=None, down=None, left=None, right=None, _all=0, snap_multiple=8 )
imaginairy/utils/outpaint.py:127
↓ 2 callersMethodprepare_inputs
( self, x: torch.Tensor, s: float, c: Dict, uc: Dict )
imaginairy/modules/sgm/diffusionmodules/guiders.py:21
↓ 2 callersMethodprocess
(self)
imaginairy/vendored/realesrgan.py:132
↓ 2 callersMethodprompt_description
(self)
imaginairy/schema.py:777
↓ 2 callersFunctionprompt_library_filepaths
Return all available category/filepath pairs.
imaginairy/enhancers/prompt_expansion.py:21
↓ 2 callersFunctionprompt_normalized
(prompt, length=130)
imaginairy/utils/__init__.py:328
↓ 2 callersMethodprompts_to_embeddings
(self, prompts: List[WeightedPrompt])
imaginairy/modules/refiners_sd.py:245
↓ 2 callersMethodprompts_to_embeddings
( self, prompts: List[WeightedPrompt] )
imaginairy/modules/refiners_sd.py:438
↓ 2 callersMethodprompts_to_embeddings
(self, prompts: List[WeightedPrompt])
imaginairy/modules/refiners_sd.py:532
↓ 2 callersFunctionpy_cpu_nms
Pure Python NMS baseline.
imaginairy/vendored/facexlib/detection/retinaface_utils.py:39
↓ 2 callersMethodq_posterior
(self, x_start, x_t, t)
imaginairy/modules/diffusion/ddpm.py:458
↓ 2 callersMethodread_image
img can be image path or cv2 loaded image.
imaginairy/vendored/facexlib/utils/face_restoration_helper.py:108
↓ 2 callersFunctionread_stored_cuda_test_nodes
()
tests/conftest.py:219
↓ 2 callersMethodregister_schedule
( self, given_betas=None, beta_schedule="linear", timesteps=1000, line
imaginairy/modules/diffusion/ddpm.py:206
↓ 2 callersMethodremap_to_used
(self, inds: torch.Tensor)
imaginairy/modules/sgm/autoencoding/regularizers/quantize.py:28
↓ 2 callersFunctionrender_fstring
Render a string formatted like an f-string using the provided variables. DANGER: This is a security risk if the fstring is user-provided.
imaginairy/weight_management/translation.py:233
↓ 2 callersFunctionresolve_path_or_url
Resolves a path or url to a local absolute file path If the path_or_url is a url, it will be downloaded to the cache directory and the path
imaginairy/utils/downloads.py:18
↓ 2 callersMethodrun
(self)
imaginairy/vendored/realesrgan.py:346
↓ 2 callersMethodsample
( self, num_steps, shape, neutral_conditioning, positive_conditioning,
imaginairy/samplers/ddim.py:36
↓ 2 callersMethodsampler_step
(self, sigma, next_sigma, denoiser, x, cond, uc=None, gamma=0.0)
imaginairy/modules/sgm/diffusionmodules/sampling.py:98
↓ 2 callersFunctionsave_image_result
( result, base_count: int, outdir: str | Path, output_file_extension: str, primary_filenam
imaginairy/api/generate.py:123
↓ 2 callersFunctionsave_model_info
(model_name, component_name, format_name, info_type, data)
imaginairy/weight_management/utils.py:28
↓ 2 callersMethodsegmap_to_color
(segmap: "Tensor", palette=ade20_palette)
imaginairy/img_processors/segformer_b2_clothes.py:57
↓ 2 callersMethodset_clip_image_embedding
(self, image_embedding: Tensor)
imaginairy/vendored/refiners/foundationals/latent_diffusion/image_prompt.py:413
↓ 2 callersMethodset_downsample
(self, downsample)
imaginairy/vendored/k_diffusion/models/image_v1.py:85
↓ 2 callersMethodset_scale
(self, scale: float)
imaginairy/vendored/refiners/foundationals/latent_diffusion/image_prompt.py:409
↓ 2 callersMethodset_unet_context
(self, *, timestep: Tensor, clip_text_embedding: Tensor, **_: Tensor)
imaginairy/vendored/refiners/foundationals/latent_diffusion/stable_diffusion_1/model.py:55
↓ 2 callersMethodset_upsample
(self, upsample)
imaginairy/vendored/k_diffusion/models/image_v1.py:152
↓ 2 callersMethodsigma_to_idx
(self, sigma: torch.Tensor)
imaginairy/modules/sgm/diffusionmodules/denoiser.py:67
↓ 2 callersMethodsplit_to_multi_head
( self, x: Float[Tensor, "batch_size sequence_length embedding_dim"] )
imaginairy/vendored/refiners/foundationals/latent_diffusion/self_attention_guidance.py:31
↓ 2 callersFunctionssim
( img1, img2, window_size=11, window=None, size_average=True, full=False, val_rang
imaginairy/enhancers/video_interpolation/rife/msssim.py:40
↓ 2 callersFunctionssim_matlab
( img1, img2, window_size=11, window=None, size_average=True, full=False, val_rang
imaginairy/enhancers/video_interpolation/rife/msssim.py:126
↓ 2 callersMethodstart
(self)
imaginairy/utils/log_utils.py:155
↓ 2 callersMethodstop
(self)
imaginairy/utils/log_utils.py:165
↓ 2 callersMethodstructural_copy
Copy the structure of the Chain tree. This method returns a recursive copy of the Chain tree where all inner nodes (instances of Chai
imaginairy/vendored/refiners/fluxion/layers/chain.py:460
↓ 2 callersMethodstructural_copy
(self: "ReferenceOnlyControlAdapter")
imaginairy/vendored/refiners/foundationals/latent_diffusion/reference_only_control.py:142
↓ 2 callersMethodstructural_copy
(self: "TT2IAdapter")
imaginairy/vendored/refiners/foundationals/latent_diffusion/t2i_adapter.py:214
↓ 2 callersFunctionswish
(x)
imaginairy/vendored/codeformer/vqgan_arch.py:19
↓ 2 callersFunctiontensor2img
Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens
imaginairy/vendored/basicsr/img_util.py:42
↓ 2 callersFunctionthirds
gets value in the range of [0, 1] where 0 is the center of the pictures returns weight of rule of thirds [0, 1].
imaginairy/vendored/smart_crop.py:29
↓ 2 callersFunctiontile
(x, dim, n_tile)
imaginairy/vendored/blip/blip_vqa.py:228
← previousnext →501–600 of 2,992, ranked by callers