Update app.py

app.py

@@ -113,21 +113,20 @@ def load_and_prepare_model(model_id):
     #vae = AutoencoderKL.from_pretrained('cross-attention/asymmetric-autoencoder-kl-x-2',use_safetensors=False)
     #vae = AutoencoderKL.from_single_file('https://huggingface.co/ford442/sdxl-vae-bf16/mySLR/myslrVAE_v10.safetensors')
     #vaeX = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse",use_safetensors=True)
-    #vaeX = AutoencoderKL.from_pretrained('ford442/Juggernaut-XI-v11-fp32',subfolder='vae').to(torch.bfloat16)   #  ,use_safetensors=True  FAILS
+    vaeX = AutoencoderKL.from_pretrained('ford442/Juggernaut-XI-v11-fp32',subfolder='vae')   #  ,use_safetensors=True  FAILS
     #vaeX = AutoencoderKL.from_pretrained('ford442/RealVisXL_V5.0_FP64',subfolder='vae').to(torch.bfloat16)   #  ,use_safetensors=True  FAILS
     #unetX = UNet2DConditionModel.from_pretrained('ford442/RealVisXL_V5.0_BF16',subfolder='unet').to(torch.bfloat16)   #  ,use_safetensors=True  FAILS
   #  vae = AutoencoderKL.from_pretrained("BeastHF/MyBack_SDXL_Juggernaut_XL_VAE/MyBack_SDXL_Juggernaut_XL_VAE_V10(version_X).safetensors",safety_checker=None).to(torch.bfloat16)
     #sched = EulerAncestralDiscreteScheduler.from_pretrained("SG161222/RealVisXL_V5.0", subfolder='scheduler',beta_schedule="scaled_linear", steps_offset=1,timestep_spacing="trailing"))
     #sched = EulerAncestralDiscreteScheduler.from_pretrained("SG161222/RealVisXL_V5.0", subfolder='scheduler', steps_offset=1,timestep_spacing="trailing")
-     #sched = EulerAncestralDiscreteScheduler.from_pretrained('SG161222/RealVisXL_V5.0', subfolder='scheduler',beta_schedule="scaled_linear", beta_start=0.00085, beta_end=0.012, steps_offset=1,use_karras_sigmas=True)
-    #sched = EulerAncestralDiscreteScheduler.from_pretrained('ford442/RealVisXL_V5.0_BF16', subfolder='scheduler',beta_schedule="scaled_linear")
+    #sched = EulerAncestralDiscreteScheduler.from_pretrained('SG161222/RealVisXL_V5.0', subfolder='scheduler',beta_schedule="scaled_linear", beta_start=0.00085, beta_end=0.012, steps_offset=1,use_karras_sigmas=True)
     #pipeX = StableDiffusionXLPipeline.from_pretrained("SG161222/RealVisXL_V5.0").to(torch.bfloat16)
     #pipeX = StableDiffusionXLPipeline.from_pretrained("ford442/Juggernaut-XI-v11-fp32",use_safetensors=True)
     
     pipe = StableDiffusionXLPipeline.from_pretrained(
         'ford442/RealVisXL_V5.0_BF16',
-    #    'ford442/Juggernaut-XI-v11-fp32',
-        #'SG161222/RealVisXL_V5.0',
+       #'ford442/Juggernaut-XI-v11-fp32',
+      #   'SG161222/RealVisXL_V5.0',
         #torch_dtype=torch.bfloat16,
         add_watermarker=False,
        # custom_pipeline="lpw_stable_diffusion_xl",
@@ -136,25 +135,26 @@ def load_and_prepare_model(model_id):
      #  vae=AutoencoderKL.from_pretrained("BeastHF/MyBack_SDXL_Juggernaut_XL_VAE/MyBack_SDXL_Juggernaut_XL_VAE_V10(version_X).safetensors",repo_type='model',safety_checker=None),
      #   vae=AutoencoderKL.from_pretrained("stabilityai/sdxl-vae",repo_type='model',safety_checker=None, torch_dtype=torch.float32),
        # vae=AutoencoderKL.from_pretrained("ford442/sdxl-vae-bf16",repo_type='model',safety_checker=None),
-        vae=AutoencoderKL.from_pretrained('ford442/Juggernaut-XI-v11-fp32',subfolder='vae').to(torch.bfloat16),
+        #vae=vae,
         #unet=pipeX.unet,
-        scheduler = EulerAncestralDiscreteScheduler.from_pretrained('ford442/RealVisXL_V5.0_BF16', subfolder='scheduler',beta_schedule="scaled_linear"),
+        #scheduler = sched,
       #  scheduler = EulerAncestralDiscreteScheduler.from_config(pipeX.scheduler.config, beta_schedule="scaled_linear", beta_start=0.00085, beta_end=0.012, steps_offset=1)
         #scheduler=EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config, beta_schedule="scaled_linear", beta_start=0.00085, beta_end=0.012, steps_offset =1)
     )
-    
     #sched = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config, beta_schedule="scaled_linear",use_karras_sigmas=True, algorithm_type="dpmsolver++")
     #pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config, beta_schedule="scaled_linear", beta_start=0.00085, beta_end=0.012, steps_offset=1)
     #pipe.scheduler = DPMSolverMultistepScheduler.from_pretrained('SG161222/RealVisXL_V5.0', subfolder='scheduler', algorithm_type='sde-dpmsolver++')
-    #pipe.vae = vaeX   #.to(torch.bfloat16)
+    pipe.vae = vaeX.to(torch.bfloat16)
     #pipe.unet = unetX
     #pipe.vae.do_resize=False
-    #pipe.scheduler = sched
     #pipe.vae=vae.to(torch.bfloat16)
     #pipe.unet=pipeX.unet
     #pipe.scheduler=EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config, beta_schedule="scaled_linear", beta_start=0.00085, beta_end=0.012, steps_offset=1)
 
     pipe.to(device)
+    
+    pipe.scheduler = EulerAncestralDiscreteScheduler.from_pretrained('ford442/RealVisXL_V5.0_BF16', subfolder='scheduler',beta_schedule="scaled_linear")
+    
     pipe.to(torch.bfloat16)
     
     #apply_hidiffusion(pipe)
@@ -222,7 +222,7 @@ def uploadNote():
         f.write(f"Guidance Scale: {guidance_scale} \n")
         f.write(f"SPACE SETUP: \n")
         f.write(f"Use Model Dtype: no \n")
-        f.write(f"Model Scheduler: Euler_a custom before cuda \n")
+        f.write(f"Model Scheduler: Euler_a custom after cuda \n")
         f.write(f"Model VAE: juggernaut to bfloat before cuda \n")
         f.write(f"Model UNET: default ford442/RealVisXL_V5.0_BF16 \n")
         f.write(f"Model HiDiffusion OFF \n")