Update app.py

app.py

@@ -55,7 +55,7 @@ text_encoder = CLIPTextModel.from_pretrained(
     'JingyeChen22/textdiffuser2-full-ft', subfolder="text_encoder"
 ).cuda().half()
 tokenizer = CLIPTokenizer.from_pretrained(
-    'botp/stable-diffusion-v1-5', subfolder="tokenizer"
+    'stable-diffusion-v1-5/stable-diffusion-v1-5', subfolder="tokenizer"
 )
 
 #### additional tokens are introduced, including coordinate tokens and character tokens
@@ -71,7 +71,7 @@ for c in alphabet:
 print(len(tokenizer))
 print('***************')
 
-vae = AutoencoderKL.from_pretrained('botp/stable-diffusion-v1-5', subfolder="vae").half().cuda()
+vae = AutoencoderKL.from_pretrained('stable-diffusion-v1-5/stable-diffusion-v1-5', subfolder="vae").half().cuda()
 unet = UNet2DConditionModel.from_pretrained(
     'JingyeChen22/textdiffuser2-full-ft', subfolder="unet"
 ).half().cuda()
@@ -372,7 +372,7 @@ def text_to_image(guest_id, prompt,keywords,positive_prompt,radio,slider_step,sl
             prompts_cond = torch.Tensor(prompts_cond).long().cuda()
             prompts_nocond = torch.Tensor(prompts_nocond).long().cuda()
 
-            scheduler = DDPMScheduler.from_pretrained('botp/stable-diffusion-v1-5', subfolder="scheduler") 
+            scheduler = DDPMScheduler.from_pretrained('stable-diffusion-v1-5/stable-diffusion-v1-5', subfolder="scheduler") 
             scheduler.set_timesteps(slider_step) 
             noise = torch.randn((slider_batch, 4, 64, 64)).to("cuda").half()
             input = noise