Update app.py

app.py

@@ -5,7 +5,11 @@ from huggingface_hub import hf_hub_download
 from safetensors.torch import load_file
 
 ### SDXL Turbo #### 
-pipe_turbo = StableDiffusionXLPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16")
+pipe_turbo = StableDiffusionXLPipeline.from_pretrained("stabilityai/sdxl-turbo",
+                                                       vae=vae,
+                                                       torch_dtype=torch.float16,
+                                                       variant="fp16"
+                                                      )
 pipe_turbo.to("cuda")
 
 ### SDXL Lightning ### 
@@ -13,9 +17,19 @@ base = "stabilityai/stable-diffusion-xl-base-1.0"
 repo = "ByteDance/SDXL-Lightning"
 ckpt = "sdxl_lightning_1step_unet_x0.safetensors" 
 
-unet = UNet2DConditionModel.from_config(base, subfolder="unet").to("cuda", torch.float16)
-unet.load_state_dict(load_file(hf_hub_download(repo, ckpt), device="cuda"))
-pipe_lightning = StableDiffusionXLPipeline.from_pretrained(base, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
+unet = UNet2DConditionModel.from_config(base, subfolder="unet").to(torch.float16)
+unet.load_state_dict(load_file(hf_hub_download(repo, ckpt)))
+pipe_lightning = StableDiffusionXLPipeline.from_pretrained(base,
+                                                           unet=unet,
+                                                           vae=vae,
+                                                           text_encoder=pipe_turbo.text_encoder,
+                                                           text_encoder_2=pipe_turbo.text_encoder_2,
+                                                           tokenizer=pipe_turbo.tokenizer,
+                                                           tokenizer_2=pipe_turbo.tokenizer_2,
+                                                           torch_dtype=torch.float16,
+                                                           variant="fp16"
+                                                          )#.to("cuda")
+del unet
 pipe_lightning.scheduler = EulerDiscreteScheduler.from_config(pipe_lightning.scheduler.config, timestep_spacing="trailing", prediction_type="sample")
 pipe_lightning.to("cuda")
 
@@ -23,11 +37,21 @@ pipe_lightning.to("cuda")
 repo_name = "ByteDance/Hyper-SD"
 ckpt_name = "Hyper-SDXL-1step-Unet.safetensors"
 
-unet = UNet2DConditionModel.from_config(base, subfolder="unet").to("cuda", torch.float16)
-unet.load_state_dict(load_file(hf_hub_download(repo_name, ckpt_name), device="cuda"))
-pipe_hyper = StableDiffusionXLPipeline.from_pretrained(base, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
+unet = UNet2DConditionModel.from_config(base, subfolder="unet").to(torch.float16)
+unet.load_state_dict(load_file(hf_hub_download(repo_name, ckpt_name)))
+pipe_hyper = StableDiffusionXLPipeline.from_pretrained(base,
+                                                       unet=unet,
+                                                       vae=vae,
+                                                       text_encoder=pipe_turbo.text_encoder,
+                                                       text_encoder_2=pipe_turbo.text_encoder_2,
+                                                       tokenizer=pipe_turbo.tokenizer,
+                                                       tokenizer_2=pipe_turbo.tokenizer_2,
+                                                       torch_dtype=torch.float16,
+                                                       variant="fp16"
+                                                      )#.to("cuda")
 pipe_hyper.scheduler = LCMScheduler.from_config(pipe_hyper.scheduler.config)
 pipe_hyper.to("cuda")
+del unet
 
 def run_comparison(prompt):
     image_turbo=pipe_turbo(prompt=prompt, num_inference_steps=1, guidance_scale=0).images[0]