Merge branch 'main' of https://huggingface.co/spaces/multimodalart/mindseye

README.md

@@ -1,5 +1,5 @@
 ---
-title: MindsEye
+title: MindsEye Lite
 emoji: 💻
 colorFrom: pink
 colorTo: yellow

app.py

@@ -21,7 +21,6 @@ def text2image_latent(text,steps,width,height,images,diversity):
         image_str = image_str.replace("data:image/png;base64,","")
         decoded_bytes = base64.decodebytes(bytes(image_str, "utf-8"))
         img = Image.open(io.BytesIO(decoded_bytes))
-        #image_arrays.append(numpy.asarray(img))
         url = shortuuid.uuid()
         temp_dir = './tmp'
         if not os.path.exists(temp_dir):
@@ -39,16 +38,15 @@ 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)
+def text2image_diffusion(text,steps_diff, images_diff, weight, clip):
+    results = diffusion(text, steps_diff, images_diff, weight, clip)
     image_paths = []
     image_arrays = []
     for image in results:
-        image_str = image[0]
+        image_str = image
         image_str = image_str.replace("data:image/png;base64,","")
         decoded_bytes = base64.decodebytes(bytes(image_str, "utf-8"))
         img = Image.open(io.BytesIO(decoded_bytes))
-        #image_arrays.append(numpy.asarray(img))
         url = shortuuid.uuid()
         temp_dir = './tmp'
         if not os.path.exists(temp_dir):
@@ -87,16 +85,16 @@ with gr.Blocks() as mindseye:
                     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)
+                    steps_vq = 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)
+                    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)
+                    get_image_diffusion = gr.Button("Generate Image",css=css_mt)
         with gr.Row():
             with gr.Tabs():
                 #with gr.TabItem("Image output"):
@@ -106,6 +104,6 @@ with gr.Blocks() as mindseye:
     
     get_image_latent.click(text2image_latent, inputs=[text,steps,width,height,images,diversity], outputs=gallery)
     get_image_rudalle.click(text2image_rudalle, inputs=[text,aspect,model], outputs=gallery)
-    get_image_vqgan.click(text2image_vqgan, inputs=[text,width_vq,height_vq,style,steps,flavor],outputs=gallery)
-    get_image_diffusion.click(text2image_diffusion, inputs=[steps_diff, images_diff, weight, clip],outputs=gallery)
+    get_image_vqgan.click(text2image_vqgan, inputs=[text,width_vq,height_vq,style,steps_vq,flavor],outputs=gallery)
+    get_image_diffusion.click(text2image_diffusion, inputs=[text, steps_diff, images_diff, weight, clip],outputs=gallery)
 mindseye.launch()