Code for generation of text and image

app.py

@@ -0,0 +1,92 @@
+from transformers import pipeline
+import gradio as gr
+import re
+import torch
+from torch import autocast
+from diffusers import StableDiffusionPipeline
+
+# Available models for pipeline
+# checkpoint = 'wvangils/CTRL-Beatles-Lyrics-finetuned-newlyrics'
+# checkpoint = 'wvangils/GPT-Medium-Beatles-Lyrics-finetuned-newlyrics'
+# checkpoint = 'wvangils/GPT-Neo-125m-Beatles-Lyrics-finetuned-newlyrics'
+# checkpoint = 'wvangils/GPT2-Beatles-Lyrics-finetuned-newlyrics'
+# checkpoint = 'wvangils/DistilGPT2-Beatles-Lyrics-finetuned-newlyrics'
+# checkpoint = 'wvangils/BLOOM-350m-Beatles-Lyrics-finetuned-newlyrics'
+
+checkpoint_choices = ['wvangils/GPT-Medium-Beatles-Lyrics-finetuned-newlyrics', 'wvangils/GPT-Neo-125m-Beatles-Lyrics-finetuned-newlyrics', 'wvangils/BLOOM-560m-Beatles-Lyrics-finetuned']
+
+# Create function for generation
+
+def generate_beatles(checkpoint, input_prompt, temperature, top_p):
+
+    # Create generator for different models
+
+    generator = pipeline("text-generation", model=checkpoint)
+    generated_lyrics = generator(input_prompt
+                              , max_length = 50
+                              , num_return_sequences = 1
+                              , return_full_text = True
+                              , verbose = 0
+                              #, num_beams = 1
+                              #, early_stopping = True    # Werkt niet goed lijkt 
+                              , temperature = temperature    
+                              #, top_k = 50     # Default 50
+                              , top_p = top_p    # Default 1.0
+                              , no_repeat_ngram_size = 3   # Default = 0
+                              , repetition_penalty = 1.0   # Default = 1.0
+                              #, do_sample = True     # Default = False
+                              )[0]["generated_text"]
+
+    lyrics_sentences = re.sub('\n', '. ', generated_lyrics)
+    title_generator = pipeline('summarization', model='czearing/story-to-title')
+    title = title_generator(lyrics_sentences, min_length=1, max_length=10, repetition_penalty=2.5)[0]['summary_text']
+
+    pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4"
+                                                , revision="fp16"
+                                                , torch_dtype=torch.float16
+                                                #, use_auth_token=True
+                                                , use_auth_token="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")  
+
+    # And move the pipeline to GPU
+    pipe = pipe.to("cuda")    
+
+    # Set a seed for reproducebility
+    seed = torch.Generator("cuda").manual_seed(42)
+    image_input = "Oil painting for " + title
+
+    # Generate the image, [PIL format](https://pillow.readthedocs.io/en/stable/)
+    with autocast("cuda"):
+      image = pipe(image_input, num_inference_steps=50, generator=seed, guidance_scale=8.5)["sample"][0] 
+
+    return (title, generated_lyrics, image)
+
+# Create textboxes for input and output
+input_box = gr.Textbox(label="Input prompt:", placeholder="Write the start of a song here", value="In my dreams I am", lines=2, max_lines=5)
+gen_lyrics = gr.Textbox(label="Lyrics by The Beatles and chosen language model:", lines=15)
+gen_title = gr.Textbox(label="Proposed songtitle", lines=1) 
+gen_image = gr.Image(label="Proposed song cover", type="pil")
+
+# Layout and text above the App
+title='Beatles lyrics generator'
+description="<p style='text-align: center'>Multiple language models were fine-tuned on lyrics from The Beatles to generate Beatles-like text. Give it a try!</p>"
+article="""<p style='text-align: left'>A couple of data scientists working for <a href='https://cmotions.nl/' target="_blank">Cmotions</a> came together to construct a text generation model that will output Beatles-like text. 
+        We tried several text generation models that we were able to load in Colab: a general <a href='https://huggingface.co/gpt2-medium' target='_blank'>GPT2-medium</a> model, the Eleuther AI small-sized GPT model <a href='https://huggingface.co/EleutherAI/gpt-neo-125M' target='_blank'>GPT-Neo</a> and the new kid on the block build by the <a href='https://bigscience.notion.site/BLOOM-BigScience-176B-Model-ad073ca07cdf479398d5f95d88e218c4' target='_blank'>Bigscience</a> initiative <a href='bigscience/bloom-350m' target='_blank'>BLOOM 350m</a>. 
+        Further we've put together a <a href='https://huggingface.co/datasets/cmotions/Beatles_lyrics' target='_blank'> Huggingface dataset</a> containing all known lyrics created by The Beatles. <a href='https://www.theanalyticslab.nl/blogs/' target='_blank'>Read this blog </a> to see how this model was build in a Python notebook using Huggingface.
+        The default output contains 100 tokens and has a repetition penalty of 1.0. 
+         </p>"""
+
+# Let users select their own temperature and top-p
+temperature = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, label="Temperature (high = sensitive for low probability tokens)", value=0.7, show_label=True)
+top_p = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, label="Top-p (sample next possible words from given probability p)", value=0.5, show_label=True)
+checkpoint = gr.Radio(checkpoint_choices, value='wvangils/GPT-Medium-Beatles-Lyrics-finetuned-newlyrics', interactive=True, label = 'Select fine-tuned model', show_label=True)
+
+# Use generate Beatles function in demo-app Gradio
+gr.Interface(fn=generate_beatles
+             , inputs=[checkpoint, input_box, temperature, top_p]
+             , outputs=[gen_title, gen_lyrics, gen_image]
+             #, examples=examples # output is not very fancy as you have to specify all inputs for every example
+             , title=title
+             , description=description
+             , article=article
+             , allow_flagging='never'
+             ).launch()