Attempt to add vqgan and diffusion

app.py

@@ -8,10 +8,10 @@ import shortuuid
 
 latent = gr.Interface.load("spaces/multimodalart/latentdiffusion")
 rudalle = gr.Interface.load("spaces/multimodalart/rudalle")
+diffusion = gr.Interface.load("spaces/multimodalart/diffusion")
+print(diffusion)
+vqgan = gr.Interface.load("spaces/multimodalart/vqgan")
 
-#print(rudalle)
-#guided = gr.Interface.load("spaces/EleutherAI/clip-guided-diffusion")
-#print(guided)
 def text2image_latent(text,steps,width,height,images,diversity):
     results = latent(text, steps, width, height, images, diversity)
     image_paths = []
@@ -35,11 +35,14 @@ def text2image_rudalle(text,aspect,model):
     image = rudalle(text,aspect,model)[0]
     return(image)
 
-#def text2image_guided(text):
-#    image = guided(text, None, 10, 600, 0, 0, 0, random.randint(0,2147483647), None, 50, 32)
-#    print(image)
-#    image = image[0]
-#    return(image)
+def text2image_vqgan(text,width,height,style,steps,flavor):
+    results = vqgan(text,width,height,style,steps,flavor)
+    return(results)
+
+def text2image_diffusion(steps_diff, images_diff, weight, clip):
+    results = diffusion(steps_diff, images_diff, weight, clip)
+    print(results)
+    return(results)
 
 css_mt = {"margin-top": "1em"}
 
@@ -53,21 +56,33 @@ with gr.Blocks() as mindseye:
         with gr.Row():
             with gr.Tabs():
                 with gr.TabItem("Latent Diffusion"):
+                    gr.Markdown("Latent Diffusion is the state of the art of open source text-to-image models, superb in text synthesis. Sometimes struggles with complex prompts")
                     steps = gr.inputs.Slider(label="Steps - more steps can increase quality but will take longer to generate",default=45,maximum=50,minimum=1,step=1)
                     width = gr.inputs.Slider(label="Width", default=256, step=32, maximum=256, minimum=32)
                     height = gr.inputs.Slider(label="Height", default=256, step=32, maximum = 256, minimum=32)
                     images = gr.inputs.Slider(label="Images - How many images you wish to generate", default=2, step=1, minimum=1, maximum=4)
                     diversity = gr.inputs.Slider(label="Diversity scale - How different from one another you wish the images to be",default=5.0, minimum=1.0, maximum=15.0)
                     get_image_latent = gr.Button("Generate Image",css=css_mt)
-                    
                 with gr.TabItem("ruDALLE"):
+                    gr.Markdown("ruDALLE is a replication of DALL-E 1 in the russian language. No worries, your prompts will be translated automatically to russian. In case you see an error, try again a few times")
                     aspect = gr.inputs.Radio(label="Aspect Ratio", choices=["Square", "Horizontal", "Vertical"],default="Square")
                     model = gr.inputs.Dropdown(label="Model", choices=["Surrealism","Realism", "Emoji"], default="Surrealism")
                     get_image_rudalle = gr.Button("Generate Image",css=css_mt)
                 with gr.TabItem("VQGAN+CLIP"):
-                    pass
-                with gr.TabItem("V-Diffusion"):
-                    pass
+                    gr.Markdown("VQGAN+CLIP is the most famous text-to-image generator. Can produce good artistic results")
+                    width_vq = gr.inputs.Slider(label="Width", default=256, minimum=32, step=32, maximum=512)
+                    height_vq= gr.inputs.Slider(label="Height", default=256, minimum=32, step=32, maximum=512)
+                    style = gr.inputs.Dropdown(label="Style - Hyper Fast Results is fast but compromises a bit of the quality",choices=["Default","Balanced","Detailed","Consistent Creativity","Realistic","Smooth","Subtle MSE","Hyper Fast Results"],default="Hyper Fast Results")
+                    steps = gr.inputs.Slider(label="Steps - more steps can increase quality but will take longer to generate. All styles that are not Hyper Fast need at least 200 steps",default=50,maximum=300,minimum=1,step=1)
+                    flavor = gr.inputs.Dropdown(label="Flavor - pick a flavor for the style of the images, based on the images below",choices=["ginger", "cumin", "holywater", "zynth", "wyvern", "aaron", "moth", "juu"])
+                    get_image_vqgan = gr.button("Generate Image",css=css_mt)
+                with gr.TabItem("Guided Diffusion"):
+                    gr.Markdown("Guided Diffusion models produce superb quality results. V-Diffusion is its latest implementation")
+                    steps_diff = gr.inputs.Slider(label="Steps - more steps can increase quality but will take longer to generate",default=40,maximum=80,minimum=1,step=1)
+                    images_diff = gr.inputs.Slider(label="Number of images in parallel", default=2, maximum=4, minimum=1, step=1)
+                    weight = gr.inputs.Slider(label="Weight - how closely the image should resemble the prompt", default=5, maximum=15, minimum=0, step=1)
+                    clip = gr.inputs.Checkbox(label="CLIP Guided - improves coherence with complex prompts, makes it slower")
+                    get_image_diffusion = gr.button("Generate Image",css=css_mt)
         with gr.Row():
             with gr.Tabs():
                 with gr.TabItem("Image output"):
@@ -77,4 +92,6 @@ with gr.Blocks() as mindseye:
     
     get_image_latent.click(text2image_latent, inputs=[text,steps,width,height,images,diversity], outputs=[image,gallery])
     get_image_rudalle.click(text2image_rudalle, inputs=[text,aspect,model], outputs=image)
+    get_image_vqgan.click(text2image_vqgan, inputs=[text,width_vq,height_vq,style,steps,flavor],outputs=image)
+    get_image_diffusion.click(text2image_diffusion, inputs=[steps_diff, images_diff, weight, clip],outputs=gallery)
 mindseye.launch()