Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-import numpy as numpy
+import numpy as np
 from diffusers import StableDiffusionXLControlNetInpaintPipeline
 from diffusers import StableDiffusionXLImg2ImgPipeline, DPMSolverMultistepScheduler, AutoencoderTiny, StableDiffusionXLControlNetPipeline, ControlNetModel
 from diffusers.utils import load_image
@@ -30,7 +30,22 @@ controlnets = [
     ),
 ]
 
-def ourhood_inference(prompt1=str,num_inference_steps=int,scaffold=int):
+pipe_CN = StableDiffusionXLControlNetPipeline.from_pretrained("SG161222/RealVisXL_V5.0", torch_dtype=torch.float16,controlnet=controlnets, use_safetensors=True, variant='fp16')
+pipe_CN.vae = AutoencoderTiny.from_pretrained("madebyollin/taesdxl", torch_dtype=torch.float16)
+pipe_CN.scheduler=DPMSolverSDEScheduler.from_pretrained("SG161222/RealVisXL_V5.0",subfolder="scheduler",use_karras_sigmas=True)
+    ###pipe_CN.scheduler=DPMSolverMultistepScheduler.from_pretrained("SG161222/RealVisXL_V5.0",subfolder="scheduler",use_karras_sigmas=True)
+    ###pipe_CN.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
+pipe_CN.to("cuda")
+pipe_CN.load_lora_weights('CreativesCombined/hb8_cases_dreambooth_lora_test_1_14', weight_name='pytorch_lora_weights.safetensors',adapter_name='cases')
+
+refiner = StableDiffusionXLImg2ImgPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0",text_encoder_2=pipe_CN.text_encoder_2,vae=pipe_CN.vae,torch_dtype=torch.float16,use_safetensors=True,variant="fp16")
+refiner.to("cuda")
+
+pipe_IN = StableDiffusionXLControlNetInpaintPipeline.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1",controlnet=controlnets, torch_dtype=torch.float16, variant="fp16").to("cuda")
+pipe_IN.load_lora_weights('Tonioesparza/ourhood_training_dreambooth_lora_2_0', weight_name='pytorch_lora_weights.safetensors',adapter_name='ourhood')
+pipe_IN.to("cuda")
+
+def ourhood_inference(prompt1=str,num_inference_steps=int,scaffold=int,seed=int):
 
 ###pro_encode = pipe_cn.encode_text(prompt)
 
@@ -44,22 +59,17 @@ def ourhood_inference(prompt1=str,num_inference_steps=int,scaffold=int):
                   'canny_image':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/mask_depth_solo_square.png"},
                2:{'mask1':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/mask_in_C.png",
                   'depth_image':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/depth_C.png",
-                  'canny_image':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/canny_C.png"},
+                  'canny_image':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/canny_C_solo.png"},
                3:{'mask1':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/mask_in_B.png",
                   'depth_image':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/depth_B.png",
-                  'canny_image':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/canny_B.png"}}
+                  'canny_image':"https://huggingface.co/Tonioesparza/ourhood_training_dreambooth_lora_2_0/blob/main/canny_B_solo.png"}}
 
 
-    pipe_CN = StableDiffusionXLControlNetPipeline.from_pretrained("SG161222/RealVisXL_V5.0", torch_dtype=torch.float16,controlnet=controlnets[0], use_safetensors=True, variant='fp16')
-    pipe_CN.vae = AutoencoderTiny.from_pretrained("madebyollin/taesdxl", torch_dtype=torch.float16)
-    pipe_CN.scheduler=DPMSolverSDEScheduler.from_pretrained("SG161222/RealVisXL_V5.0",subfolder="scheduler",use_karras_sigmas=True)
-    ###pipe_CN.scheduler=DPMSolverMultistepScheduler.from_pretrained("SG161222/RealVisXL_V5.0",subfolder="scheduler",use_karras_sigmas=True)
-    ###pipe_CN.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
-    pipe_CN.to("cuda")
+    
 
     ##############################load loras
 
-    pipe_CN.load_lora_weights('CreativesCombined/hb8_cases_dreambooth_lora_test_1_14', weight_name='pytorch_lora_weights.safetensors',adapter_name='cases')
+    
     ###pipe_CN.fuse_lora()
 
     output_height = 1024
@@ -70,7 +80,7 @@ def ourhood_inference(prompt1=str,num_inference_steps=int,scaffold=int):
     ###ip_images init
     ###ip_img_1 = load_image(r"C:\Users\AntonioEsparzaGlisma\PycharmProjects\hB8\Cases\a-place-to_210930_HAY_A-PLACE-TO_091-768x1024.png")
     ###ip_images = [[ip_img_1]]
-    pipe_CN.set_ip_adapter_scale([[0.7]])
+    ###pipe_CN.set_ip_adapter_scale([[0.7]])
     n_steps = num_inference_steps
     ###precomputed depth image
     depth_image = load_image(scaff_dic[scaffold]['depth_image'])
@@ -89,18 +99,17 @@ def ourhood_inference(prompt1=str,num_inference_steps=int,scaffold=int):
             num_inference_steps=n_steps,
             num_images_per_prompt=1,
             generator=generator,
-            denoising_end=0.9,
-            image=images_CN[0],
+            denoising_end=0.8,
+            image=images_CN,
             output_type="latent",
-            control_guidance_end=0.25,
-            controlnet_conditioning_scale=0.5,
+            control_guidance_start=[0.0,0.5],
+            control_guidance_end=[0.5,1.0],
+            controlnet_conditioning_scale=[0.5,1.0],
         ).images[0]
 
-    refiner = StableDiffusionXLImg2ImgPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0",text_encoder_2=pipe_CN.text_encoder_2,vae=pipe_CN.vae,torch_dtype=torch.float16,use_safetensors=True,variant="fp16")
-    refiner.to("cuda")
 
-    del pipe_CN
-    torch.cuda.empty_cache()
+
+
 
     image = refiner(
         prompt=prompt1,
@@ -108,12 +117,9 @@ def ourhood_inference(prompt1=str,num_inference_steps=int,scaffold=int):
         denoising_start=0.8,
         image=results).images[0]
 
-    del refiner
-    torch.cuda.empty_cache()
 
-    pipe_IN = StableDiffusionXLControlNetInpaintPipeline.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1",controlnet=controlnets, torch_dtype=torch.float16, variant="fp16").to("cuda")
-    pipe_IN.load_lora_weights('Tonioesparza/ourhood_training_dreambooth_lora_2_0', weight_name='pytorch_lora_weights.safetensors',adapter_name='ourhood')
-    pipe_IN.to("cuda")
+
+
 
     image = pipe_IN(
             prompt=prompt2,
@@ -121,16 +127,15 @@ def ourhood_inference(prompt1=str,num_inference_steps=int,scaffold=int):
             image=image,
             mask_image=mask1,
             num_inference_steps=n_steps,
-            strength=0.95,
-            control_guidance_end=[0.3,0.9],
+            strength=1.0,
+            control_guidance_end=[0.9,0.9],
             controlnet_conditioning_scale=[0.3, 0.45],
             control_image=images_CN,
             generator=generator,
         ).images[0]
 
-    image.show()
-    del pipe_IN
-    torch.cuda.empty_cache()
+
+
 
     return image
 
@@ -201,17 +206,9 @@ with gr.Blocks(css=css) as demo:
                 value=0,
             )
             
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
 
             with gr.Row():
 
-                fracc = gr.Slider(
-                    label="¨seed",
-                    minimum=0,
-                    maximum=9999,
-                    step=1,
-                    value=0, #Replace with defaults that work for your model
-                )
                 
                 num_inference_steps = gr.Slider(
                     label="Number of inference steps",
@@ -228,7 +225,7 @@ with gr.Blocks(css=css) as demo:
     gr.on(
         triggers=[run_button.click, prompt.submit],
         fn = ourhood_inference,
-        inputs = [prompt, num_inference_steps, perspective],
+        inputs = [prompt, num_inference_steps, perspective,seed],
         outputs = [result]
     )