Update app.py

app.py

@@ -96,14 +96,14 @@ isomer_color_weights = torch.from_numpy(np.array([1, 0.5, 1, 0.5])).float().to(d
 
 # model initialization and loading
 # flux
-# taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=torch.bfloat16).to(device_0)
-# good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=torch.bfloat16, token=access_token).to(device_0)
-flux_pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, token=access_token).to(device=device_0, dtype=torch.bfloat16)
-# flux_pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, vae=taef1, token=access_token).to(device_0)
-flux_lora_ckpt_path = hf_hub_download(repo_id="LTT/xxx-ckpt", filename="rgb_normal_large.safetensors", repo_type="model", token=access_token)
-flux_pipe.load_lora_weights(flux_lora_ckpt_path)
-flux_pipe.to(device=device_0, dtype=torch.bfloat16)
-torch.cuda.empty_cache()
+# # taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=torch.bfloat16).to(device_0)
+# # good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=torch.bfloat16, token=access_token).to(device_0)
+# flux_pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, token=access_token).to(device=device_0, dtype=torch.bfloat16)
+# # flux_pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, vae=taef1, token=access_token).to(device_0)
+# flux_lora_ckpt_path = hf_hub_download(repo_id="LTT/xxx-ckpt", filename="rgb_normal_large.safetensors", repo_type="model", token=access_token)
+# flux_pipe.load_lora_weights(flux_lora_ckpt_path)
+# flux_pipe.to(device=device_0, dtype=torch.bfloat16)
+# torch.cuda.empty_cache()
 # flux_pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(flux_pipe)
 
 
@@ -306,7 +306,7 @@ def reconstruct_3d_model(images, prompt):
 @spaces.GPU
 def gradio_pipeline(prompt, seed):
     # 生成多视图图像
-    rgb_normal_grid = generate_multi_view_images(prompt, seed)
+    # rgb_normal_grid = generate_multi_view_images(prompt, seed)
     # rgb_normal_grid = np.load("rgb_normal_grid.npy")
     image_preview = Image.fromarray((rgb_normal_grid[0] * 255).astype(np.uint8))
 
@@ -314,8 +314,8 @@ def gradio_pipeline(prompt, seed):
 
 
     # 重建 3D 模型并返回 glb 路径
-    # save_glb_addr = reconstruct_3d_model(rgb_normal_grid, prompt)
-    save_glb_addr = None
+    save_glb_addr = reconstruct_3d_model(rgb_normal_grid, prompt)
+    # save_glb_addr = None
     return image_preview, save_glb_addr
 
 # Gradio Blocks 应用