Update app.py

app.py

@@ -1,12 +1,18 @@
 import gradio as gr
-from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler, LCMScheduler
+from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler, LCMScheduler, AutoencoderKL
 import torch
 from huggingface_hub import hf_hub_download
 from safetensors.torch import load_file
 import spaces
 
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+
 ### 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 ### 
@@ -16,7 +22,16 @@ ckpt = "sdxl_lightning_1step_unet_x0.safetensors"
 
 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, torch_dtype=torch.float16, variant="fp16")#.to("cuda")
+pipe_lightning = StableDiffusionXLPipeline.from_pretrained(base,
+                                                           unet=unet,
+                                                           vae=vae,
+                                                           text_encoder_1=pipe_turbo.text_encoder_1,
+                                                           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")
@@ -27,7 +42,16 @@ ckpt_name = "Hyper-SDXL-1step-Unet.safetensors"
 
 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, torch_dtype=torch.float16, variant="fp16")#.to("cuda")
+pipe_hyper = StableDiffusionXLPipeline.from_pretrained(base,
+                                                       unet=unet,
+                                                       vae=vae,
+                                                       text_encoder_1=pipe_turbo.text_encoder_1,
+                                                       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