first commit

app.py

@@ -0,0 +1,132 @@
+import torch
+import gradio as gr
+from diffusers import StableDiffusionImg2ImgPipeline
+from diffusers import DDIMScheduler,EulerDiscreteScheduler,EulerAncestralDiscreteScheduler,UniPCMultistepScheduler
+from diffusers import  KDPM2DiscreteScheduler,KDPM2AncestralDiscreteScheduler,PNDMScheduler
+from diffusers import DPMSolverMultistepScheduler
+import random
+
+
+
+
+def set_pipeline(model_id_repo,scheduler):
+
+    model_ids_dict = {
+    "dreamshaper": "Lykon/DreamShaper",
+    "deliberate": "soren127/Deliberate",
+    "runwayml": "runwayml/stable-diffusion-v1-5",
+    "Realistic_Vision_V5_1_noVAE":"SG161222/Realistic_Vision_V5.1_noVAE"
+}
+    model_id = model_id_repo
+    model_repo = model_ids_dict.get(model_id)
+    print("model_repo :",model_repo)
+
+
+    pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
+        model_repo,
+        # torch_dtype=torch.float16,                               # to run on cpu
+        use_safetensors=True,
+    ).to("cpu")
+
+    # pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
+    #     model_repo,
+    #     torch_dtype=torch.float16,                               # to run on cpu
+    #     use_safetensors=True,
+    # ).to("cuda")
+
+
+    scheduler_classes = {
+        "DDIM": DDIMScheduler,
+        "Euler": EulerDiscreteScheduler,
+        "Euler a": EulerAncestralDiscreteScheduler,
+        "UniPC": UniPCMultistepScheduler,
+        "DPM2 Karras": KDPM2DiscreteScheduler,
+        "DPM2 a Karras": KDPM2AncestralDiscreteScheduler,
+        "PNDM": PNDMScheduler,
+        "DPM++ 2M Karras": DPMSolverMultistepScheduler,
+        "DPM++ 2M SDE Karras": DPMSolverMultistepScheduler,
+    }
+
+    sampler_name = scheduler  # Example sampler name, replace with the actual value
+    scheduler_class = scheduler_classes.get(sampler_name)
+
+    if scheduler_class is not None:
+        print("sampler_name:",sampler_name)
+        pipe.scheduler = scheduler_class.from_config(pipe.scheduler.config)
+    else:
+        pass  
+
+    return pipe
+
+
+def img_args(
+             prompt,
+             negative_prompt,
+             init_img,
+             model_id_repo = "Realistic_Vision_V5_1_noVAE",
+             scheduler= "Euler a",
+             height=896,
+             width=896,
+             num_inference_steps = 30,
+             guidance_scale = 7.5,
+             num_images_per_prompt = 1,
+             seed = 0,
+             strength = 0.5,
+             ):
+
+    pipe = set_pipeline(model_id_repo,scheduler)
+
+    if seed == 0:
+        seed = random.randint(0,25647981548564)
+        print(f"random seed :{seed}")
+        generator = torch.manual_seed(seed)
+    else:
+        generator = torch.manual_seed(seed)
+        print(f"manual seed :{seed}")
+    
+    init_img = init_img.resize((width,height))
+    print(init_img.size)
+    image = pipe(
+                 image=init_img,
+                 prompt=prompt,
+                 negative_prompt = negative_prompt,
+                 height = height,
+                 width = width,
+                 num_inference_steps = num_inference_steps,
+                 guidance_scale = guidance_scale,
+                 num_images_per_prompt = num_images_per_prompt, # default 1
+                 generator = generator,
+                 strength=strength             
+                 ).images
+    return image
+
+
+block = gr.Blocks().queue()
+block.title = "Inpaint Anything"
+with block as image_gen:
+    with gr.Column():
+        with gr.Row():
+            gr.Markdown("## Image Generation")
+        with gr.Row():
+            with gr.Column():
+                # with gr.Row():
+                input_img = gr.Image(type="pil",label="Output")
+                prompt = gr.Textbox(placeholder="what you want to generate",label="Positive Prompt")
+                negative_prompt = gr.Textbox(placeholder="what you don't want to generate",label="Negative prompt")
+                run_btn = gr.Button("image generation", elem_id="select_btn", variant="primary")
+                with gr.Accordion(label="Advance Options",open=False):
+                    model_selection = gr.Dropdown(choices=["dreamshaper","deliberate","runwayml","Realistic_Vision_V5_1_noVAE"],value="Realistic_Vision_V5_1_noVAE",label="Models")
+                    schduler_selection = gr.Dropdown(choices=["DDIM","Euler","Euler a","UniPC","DPM2 Karras","DPM2 a Karras","PNDM","DPM++ 2M Karras","DPM++ 2M SDE Karras"],value="Euler a",label="Scheduler")
+                    strength_slider = gr.Slider(label="strength", minimum=0, maximum=1, value=0.8, step=0.05)
+                    guidance_scale_slider = gr.Slider(label="guidance_scale", minimum=0, maximum=15, value=7.5, step=0.5)
+                    num_images_per_prompt_slider = gr.Slider(label="num_images_per_prompt", minimum=0, maximum=5, value=1, step=1)
+                    width_slider = gr.Slider(label="width", minimum=0, maximum=2048, value=896, step=1)
+                    height_slider = gr.Slider(label="height", minimum=0, maximum=2048, value=896, step=1)
+                    num_inference_steps_slider = gr.Slider(label="num_inference_steps", minimum=0, maximum=150, value=30, step=1)
+                    seed_slider = gr.Slider(label="Seed Slider", minimum=0, maximum=256479815, value=0, step=1)
+            with gr.Column():
+                out_img = gr.Gallery(label='Output', show_label=False, elem_id="gallery", preview=True)
+            
+                    
+    run_btn.click(fn=img_args,inputs=[prompt,negative_prompt,input_img,model_selection,schduler_selection,height_slider,width_slider,num_inference_steps_slider,guidance_scale_slider,num_images_per_prompt_slider,seed_slider,strength_slider],outputs=[out_img])            
+image_gen.launch()