Super-squash branch 'main' using huggingface_hub

Co-authored-by: fancyfeast <[email protected]>
Co-authored-by: SmilingWolf <[email protected]>
Co-authored-by: fancyfeast <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: E621 Tagger (Z3D E621 Convnext)
+emoji: 📈
+colorFrom: blue
+colorTo: pink
+sdk: gradio
+sdk_version: 4.36.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,80 @@
+import gradio as gr
+import huggingface_hub
+from PIL import Image
+from pathlib import Path
+import onnxruntime as rt
+import numpy as np
+import csv
+import spaces
+
+import onnxruntime as rt
+e621_model_path = Path(huggingface_hub.snapshot_download('toynya/Z3D-E621-Convnext'))
+e621_model_session = rt.InferenceSession(e621_model_path / 'model.onnx', providers=["CUDAExecutionProvider", "CPUExecutionProvider"])
+with open(e621_model_path / 'tags-selected.csv', mode='r', encoding='utf-8') as file:
+	csv_reader = csv.DictReader(file)
+	e621_model_tags = [row['name'].strip() for row in csv_reader]
+
+
+def prepare_image_e621(image: Image.Image, target_size: int):
+	import numpy as np
+	# Pad image to square
+	image_shape = image.size
+	max_dim = max(image_shape)
+	pad_left = (max_dim - image_shape[0]) // 2
+	pad_top = (max_dim - image_shape[1]) // 2
+
+	padded_image = Image.new("RGB", (max_dim, max_dim), (255, 255, 255))
+	padded_image.paste(image, (pad_left, pad_top))
+
+	# Resize
+	if max_dim != target_size:
+		padded_image = padded_image.resize((target_size, target_size), Image.BICUBIC)
+	
+	# Convert to numpy array
+	# Based on the ONNX graph, the model appears to expect inputs in the range of 0-255
+	image_array = np.asarray(padded_image, dtype=np.float32)
+
+	# Convert PIL-native RGB to BGR
+	image_array = image_array[:, :, ::-1]
+
+	return np.expand_dims(image_array, axis=0)
+
+
+def predict_e621(image: Image.Image):
+	THRESHOLD = 0.3
+	image_array = prepare_image_e621(image, 448)
+
+	image_array = prepare_image_e621(image, 448)
+	input_name = 'input_1:0'
+	output_name = 'predictions_sigmoid'
+
+	result = e621_model_session.run([output_name], {input_name: image_array})
+	result = result[0][0]
+
+	scores = {e621_model_tags[i]: result[i] for i in range(len(result))}
+	predicted_tags = [tag for tag, score in scores.items() if score > THRESHOLD]
+	tag_string = ', '.join(predicted_tags).replace("_", " ")
+
+	return tag_string, scores
+
+
+DESCRIPTION = """
+E621 Tagger (Z3D-E621-Convnext) 
+- Image => E621 Pony Prompt
+- Mod of [fancyfeast's demo](https://huggingface.co/spaces/fancyfeast/Z3D-E621-Convnext-space) for toynya's [Z3D-E621-Convnext](https://huggingface.co/toynya/Z3D-E621-Convnext)
+"""
+
+gradio_app = gr.Interface(
+	predict_e621,
+	inputs=gr.Image(label="Source", sources=['upload', 'clipboard'], type='pil'),
+	outputs=[
+		gr.Textbox(label="Tag String", show_copy_button=True),
+		gr.Label(label="Tag Predictions", num_top_classes=100),
+	],
+	description=DESCRIPTION,
+	allow_flagging="never",
+)
+
+
+if __name__ == '__main__':
+	gradio_app.launch()

requirements.txt

@@ -0,0 +1,2 @@
+numpy==1.26.3
+onnxruntime==1.16.3