Stable Diffusion fix + Bloom 560m

Accelerated Gradio backend for Stable diffusion seems to be working again (at least in Colab). Also: select Bloom as default model since it has the best eval.

app.py

@@ -39,15 +39,15 @@ def get_image_input(title, given_input_style):
     return image_input, final_style
 
 # Available models for generate lyrics pipeline
-checkpoint = 'wvangils/GPT-Medium-Beatles-Lyrics-finetuned-newlyrics'
+# checkpoint = 'wvangils/GPT-Medium-Beatles-Lyrics-finetuned-newlyrics'
 # checkpoint = 'wvangils/GPT-Neo-125m-Beatles-Lyrics-finetuned-newlyrics'
-# checkpoint = 'wvangils/BLOOM-560m-Beatles-Lyrics-finetuned'
+checkpoint = 'wvangils/BLOOM-560m-Beatles-Lyrics-finetuned'
 
 # Setup all the pipelines we need
 title_generator = pipeline('summarization', model='czearing/story-to-title')
 lyrics_generator = pipeline("text-generation", model=checkpoint)
 # For the image generator we use stable diffusion from an existing HuggingFace space
-stable_diffusion = gr.Blocks.load(name="spaces/stabilityai/stable-diffusion")
+stable_diffusion = gr.Blocks.load(name="spaces/stabilityai/stable-diffusion-1")
 
 # Create 4 images for the given prompt and receive the first one
 # This function uses an existing HuggingFace space where the number of created images cannot be modified