Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

cleanup: remove unused scripts, cruft

Browse Source 
App runs & tests pass.
This commit is contained in:
psychedelicious
2024-03-19 16:54:04 +11:00
parent 6c558279dd
commit b378cfcb46
38 changed files with 23 additions and 5601 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
invokeai/backend/image_util/__init__.py
View File

@ -5,21 +5,4 @@ Initialization file for invokeai.backend.image_util methods.
from .patchmatch import PatchMatch # noqa: F401
from .pngwriter import PngWriter, PromptFormatter, retrieve_metadata, write_metadata # noqa: F401
from .seamless import configure_model_padding # noqa: F401
from .txt2mask import Txt2Mask # noqa: F401
from .util import InitImageResizer, make_grid # noqa: F401
def debug_image(debug_image, debug_text, debug_show=True, debug_result=False, debug_status=False):
from PIL import ImageDraw
if not debug_status:
return
image_copy = debug_image.copy().convert("RGBA")
ImageDraw.Draw(image_copy).text((5, 5), debug_text, (255, 0, 0))
if debug_show:
image_copy.show()
if debug_result:
return image_copy

11
invokeai/backend/image_util/depth_anything/__init__.py
View File

@ -10,11 +10,11 @@ from PIL import Image
from torchvision.transforms import Compose
from invokeai.app.services.config.config_default import get_config
from invokeai.app.util.download_with_progress import download_with_progress_bar
from invokeai.backend.image_util.depth_anything.model.dpt import DPT_DINOv2
from invokeai.backend.image_util.depth_anything.utilities.util import NormalizeImage, PrepareForNet, Resize
from invokeai.backend.util.devices import choose_torch_device
from invokeai.backend.util.logging import InvokeAILogger
from invokeai.backend.util.util import download_with_progress_bar
config = get_config()
logger = InvokeAILogger.get_logger(config=config)
@ -59,9 +59,12 @@ class DepthAnythingDetector:
self.device = choose_torch_device()
def load_model(self, model_size: Literal["large", "base", "small"] = "small"):
DEPTH_ANYTHING_MODEL_PATH = pathlib.Path(config.models_path / DEPTH_ANYTHING_MODELS[model_size]["local"])
if not DEPTH_ANYTHING_MODEL_PATH.exists():
download_with_progress_bar(DEPTH_ANYTHING_MODELS[model_size]["url"], DEPTH_ANYTHING_MODEL_PATH)
DEPTH_ANYTHING_MODEL_PATH = config.models_path / DEPTH_ANYTHING_MODELS[model_size]["local"]
download_with_progress_bar(
pathlib.Path(DEPTH_ANYTHING_MODELS[model_size]["url"]).name,
DEPTH_ANYTHING_MODELS[model_size]["url"],
DEPTH_ANYTHING_MODEL_PATH,
)
if not self.model or model_size != self.model_size:
del self.model

17
invokeai/backend/image_util/dw_openpose/wholebody.py
View File

@ -1,14 +1,13 @@
# Code from the original DWPose Implementation: https://github.com/IDEA-Research/DWPose
# Modified pathing to suit Invoke
import pathlib
import numpy as np
import onnxruntime as ort
from invokeai.app.services.config.config_default import get_config
from invokeai.app.util.download_with_progress import download_with_progress_bar
from invokeai.backend.util.devices import choose_torch_device
from invokeai.backend.util.util import download_with_progress_bar
from .onnxdet import inference_detector
from .onnxpose import inference_pose
@ -24,7 +23,7 @@ DWPOSE_MODELS = {
},
}
config = get_config
config = get_config()
class Wholebody:
@ -33,13 +32,13 @@ class Wholebody:
providers = ["CUDAExecutionProvider"] if device == "cuda" else ["CPUExecutionProvider"]
DET_MODEL_PATH = pathlib.Path(config.models_path / DWPOSE_MODELS["yolox_l.onnx"]["local"])
if not DET_MODEL_PATH.exists():
download_with_progress_bar(DWPOSE_MODELS["yolox_l.onnx"]["url"], DET_MODEL_PATH)
DET_MODEL_PATH = config.models_path / DWPOSE_MODELS["yolox_l.onnx"]["local"]
download_with_progress_bar("yolox_l.onnx", DWPOSE_MODELS["yolox_l.onnx"]["url"], DET_MODEL_PATH)
POSE_MODEL_PATH = pathlib.Path(config.models_path / DWPOSE_MODELS["dw-ll_ucoco_384.onnx"]["local"])
if not POSE_MODEL_PATH.exists():
download_with_progress_bar(DWPOSE_MODELS["dw-ll_ucoco_384.onnx"]["url"], POSE_MODEL_PATH)
POSE_MODEL_PATH = config.models_path / DWPOSE_MODELS["dw-ll_ucoco_384.onnx"]["local"]
download_with_progress_bar(
"dw-ll_ucoco_384.onnx", DWPOSE_MODELS["dw-ll_ucoco_384.onnx"]["url"], POSE_MODEL_PATH
)
onnx_det = DET_MODEL_PATH
onnx_pose = POSE_MODEL_PATH

46
invokeai/backend/image_util/invoke_metadata.py
View File

@ -1,46 +0,0 @@
# Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Development Team
"""Very simple functions to fetch and print metadata from InvokeAI-generated images."""
import json
import sys
from pathlib import Path
from typing import Any, Dict
from PIL import Image
def get_invokeai_metadata(image_path: Path) -> Dict[str, Any]:
"""
Retrieve "invokeai_metadata" field from png image.
:param image_path: Path to the image to read metadata from.
May raise:
OSError -- image path not found
KeyError -- image doesn't contain the metadata field
"""
image: Image = Image.open(image_path)
return json.loads(image.text["invokeai_metadata"])
def print_invokeai_metadata(image_path: Path):
"""Pretty-print the metadata."""
try:
metadata = get_invokeai_metadata(image_path)
print(f"{image_path}:\n{json.dumps(metadata, sort_keys=True, indent=4)}")
except OSError:
print(f"{image_path}:\nNo file found.")
except KeyError:
print(f"{image_path}:\nNo metadata found.")
print()
def main():
"""Run the command-line utility."""
image_paths = sys.argv[1:]
if not image_paths:
print(f"Usage: {Path(sys.argv[0]).name} image1 image2 image3 ...")
print("\nPretty-print InvokeAI image metadata from the listed png files.")
sys.exit(-1)
for img in image_paths:
print_invokeai_metadata(img)

114
invokeai/backend/image_util/txt2mask.py
View File

@ -1,114 +0,0 @@
"""Makes available the Txt2Mask class, which assists in the automatic
assignment of masks via text prompt using clipseg.
Here is typical usage:
from invokeai.backend.image_util.txt2mask import Txt2Mask, SegmentedGrayscale
from PIL import Image
txt2mask = Txt2Mask(self.device)
segmented = txt2mask.segment(Image.open('/path/to/img.png'),'a bagel')
# this will return a grayscale Image of the segmented data
grayscale = segmented.to_grayscale()
# this will return a semi-transparent image in which the
# selected object(s) are opaque and the rest is at various
# levels of transparency
transparent = segmented.to_transparent()
# this will return a masked image suitable for use in inpainting:
mask = segmented.to_mask(threshold=0.5)
The threshold used in the call to to_mask() selects pixels for use in
the mask that exceed the indicated confidence threshold. Values range
from 0.0 to 1.0. The higher the threshold, the more confident the
algorithm is. In limited testing, I have found that values around 0.5
work fine.
"""
import numpy as np
import torch
from PIL import Image, ImageOps
from transformers import AutoProcessor, CLIPSegForImageSegmentation
import invokeai.backend.util.logging as logger
from invokeai.app.services.config.config_default import get_config
CLIPSEG_MODEL = "CIDAS/clipseg-rd64-refined"
CLIPSEG_SIZE = 352
class SegmentedGrayscale(object):
def __init__(self, image: Image.Image, heatmap: torch.Tensor):
self.heatmap = heatmap
self.image = image
def to_grayscale(self, invert: bool = False) -> Image.Image:
return self._rescale(Image.fromarray(np.uint8(255 - self.heatmap * 255 if invert else self.heatmap * 255)))
def to_mask(self, threshold: float = 0.5) -> Image.Image:
discrete_heatmap = self.heatmap.lt(threshold).int()
return self._rescale(Image.fromarray(np.uint8(discrete_heatmap * 255), mode="L"))
def to_transparent(self, invert: bool = False) -> Image.Image:
transparent_image = self.image.copy()
# For img2img, we want the selected regions to be transparent,
# but to_grayscale() returns the opposite. Thus invert.
gs = self.to_grayscale(not invert)
transparent_image.putalpha(gs)
return transparent_image
# unscales and uncrops the 352x352 heatmap so that it matches the image again
def _rescale(self, heatmap: Image.Image) -> Image.Image:
size = self.image.width if (self.image.width > self.image.height) else self.image.height
resized_image = heatmap.resize((size, size), resample=Image.Resampling.LANCZOS)
return resized_image.crop((0, 0, self.image.width, self.image.height))
class Txt2Mask(object):
"""
Create new Txt2Mask object. The optional device argument can be one of
'cuda', 'mps' or 'cpu'.
"""
def __init__(self, device="cpu", refined=False):
logger.info("Initializing clipseg model for text to mask inference")
# BUG: we are not doing anything with the device option at this time
self.device = device
self.processor = AutoProcessor.from_pretrained(CLIPSEG_MODEL, cache_dir=get_config().cache_dir)
self.model = CLIPSegForImageSegmentation.from_pretrained(CLIPSEG_MODEL, cache_dir=get_config().cache_dir)
@torch.no_grad()
def segment(self, image: Image.Image, prompt: str) -> SegmentedGrayscale:
"""
Given a prompt string such as "a bagel", tries to identify the object in the
provided image and returns a SegmentedGrayscale object in which the brighter
pixels indicate where the object is inferred to be.
"""
if isinstance(image, str):
image = Image.open(image).convert("RGB")
image = ImageOps.exif_transpose(image)
img = self._scale_and_crop(image)
inputs = self.processor(text=[prompt], images=[img], padding=True, return_tensors="pt")
outputs = self.model(**inputs)
heatmap = torch.sigmoid(outputs.logits)
return SegmentedGrayscale(image, heatmap)
def _scale_and_crop(self, image: Image.Image) -> Image.Image:
scaled_image = Image.new("RGB", (CLIPSEG_SIZE, CLIPSEG_SIZE))
if image.width > image.height: # width is constraint
scale = CLIPSEG_SIZE / image.width
else:
scale = CLIPSEG_SIZE / image.height
scaled_image.paste(
image.resize(
(int(scale * image.width), int(scale * image.height)),
resample=Image.Resampling.LANCZOS,
),
box=(0, 0),
)
return scaled_image