Duplicate from johnsu6616/SD_Helper

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,14 @@
+---
+title: SD_Helper
+emoji: 📊
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+license: openrail
+duplicated_from: johnsu6616/SD_Helper
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,143 @@
+import random
+import re
+
+import gradio as gr
+import torch
+
+from transformers import AutoModelForCausalLM
+from transformers import AutoTokenizer
+from transformers import AutoModelForSeq2SeqLM
+
+from transformers import AutoProcessor
+
+from transformers import pipeline
+
+from transformers import set_seed
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+big_processor = AutoProcessor.from_pretrained("microsoft/git-base-coco")
+big_model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-coco")
+
+text_pipe = pipeline('text-generation', model='succinctly/text2image-prompt-generator')
+
+zh2en_model = AutoModelForSeq2SeqLM.from_pretrained('Helsinki-NLP/opus-mt-zh-en').eval()
+zh2en_tokenizer = AutoTokenizer.from_pretrained('Helsinki-NLP/opus-mt-zh-en')
+
+en2zh_model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-zh").eval()
+en2zh_tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-zh")
+
+def load_prompter():
+    prompter_model = AutoModelForCausalLM.from_pretrained("microsoft/Promptist")
+    tokenizer = AutoTokenizer.from_pretrained("gpt2")
+    tokenizer.pad_token = tokenizer.eos_token
+    tokenizer.padding_side = "left"
+    return prompter_model, tokenizer
+
+prompter_model, prompter_tokenizer = load_prompter()
+
+def generate_prompter(plain_text, max_new_tokens=75, num_return_sequences=3):
+    input_ids = prompter_tokenizer(plain_text.strip() + " Rephrase:", return_tensors="pt").input_ids
+    eos_id = prompter_tokenizer.eos_token_id
+    outputs = prompter_model.generate(
+        input_ids,
+        do_sample=False,
+        max_new_tokens=75,
+        num_beams=6,
+        num_return_sequences=num_return_sequences,
+        eos_token_id=eos_id,
+        pad_token_id=eos_id,
+        length_penalty=-1
+
+    )
+
+    output_texts = prompter_tokenizer.batch_decode(outputs, skip_special_tokens=True)
+    result = ""
+    for output_text in output_texts:
+        result.append(output_text.replace(plain_text + " Rephrase:", "").strip())
+
+    return "\n".join(result)
+
+def translate_zh2en(text):
+    with torch.no_grad():
+        text = text.replace('\n', ',').replace('\r', ',')
+        text = re.sub('^,+', ',', text)
+        encoded = zh2en_tokenizer([text], return_tensors='pt')
+        sequences = zh2en_model.generate(**encoded)
+        return zh2en_tokenizer.batch_decode(sequences, skip_special_tokens=True)[0]
+
+def translate_en2zh(text):
+    with torch.no_grad():
+        encoded = en2zh_tokenizer([text], return_tensors="pt")
+        sequences = en2zh_model.generate(**encoded)
+        return en2zh_tokenizer.batch_decode(sequences, skip_special_tokens=True)[0]
+
+def text_generate(text):
+    seed = random.randint(100, 1000000)
+    set_seed(seed)
+
+    text_in_english = translate_zh2en(text)
+    result = ""
+    for _ in range(6):
+        sequences = text_pipe(text_in_english, max_length=random.randint(60, 90), num_return_sequences=8)
+        list = []
+        for sequence in sequences:
+
+            line = sequence['generated_text'].strip()
+
+            if line != text_in_english and len(line) > (len(text_in_english) + 4) and line.endswith(
+                    (':', '-', '—')) is False:
+                list.append(line)
+
+        result = "\n".join(list)
+
+        result = re.sub('[^ ]+\.[^ ]+', '', result)
+
+        result = result.replace('<', '').replace('>', '').replace('"', '')
+        if result != '':
+            break
+
+    return result, "\n".join(translate_en2zh(line) for line in result.split("\n") if len(line) > 0) 
+
+def get_prompt_from_image(input_image):
+    image = input_image.convert('RGB')
+    pixel_values = big_processor(images=image, return_tensors="pt").to(device).pixel_values
+    generated_ids = big_model.to(device).generate(pixel_values=pixel_values, max_length=50)
+    generated_caption = big_processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    print(generated_caption)
+    return generated_caption
+
+
+with gr.Blocks() as block:
+    with gr.Column():
+        with gr.Tab('文生文'):
+            with gr.Row():
+                input_text = gr.Textbox(lines=12, label='輸入文字', placeholder='在此输入文字...')
+
+            with gr.Row():
+                txt_prompter_btn = gr.Button('執行')
+
+        with gr.Tab('圖生文'):
+            with gr.Row():
+                input_image = gr.Image(type='pil')
+
+            with gr.Row():
+                pic_prompter_btn = gr.Button('執行')
+
+    Textbox_1 = gr.Textbox(lines=6, label='輸出結果')
+    Textbox_2 = gr.Textbox(lines=6, label='中文翻譯')
+
+    txt_prompter_btn.click(
+
+        fn=text_generate,
+        inputs=input_text, 
+        outputs=[Textbox_1,Textbox_2]
+    )
+
+    pic_prompter_btn.click(
+        fn=get_prompt_from_image,
+        inputs=input_image,
+        outputs=Textbox_1
+    )
+
+block.queue(max_size=64).launch(show_api=False, enable_queue=True, debug=True, share=False, server_name='0.0.0.0')

requirements.txt

@@ -0,0 +1,5 @@
+transformers==4.27.4
+torch==2.0.0
+gradio==3.24.1
+sentencepiece==0.1.97
+sacremoses==0.0.53