Device error using low_vram_mode on gradio app

[ChuXiaoyuu]

I got a device error when I use the low vram mode...
Run it on a single RTX3060 with 12G VRAM

Traceback (most recent call last):
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/gradio/queueing.py", line 625, in process_events
response = await route_utils.call_process_api(
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/gradio/route_utils.py", line 322, in call_process_api
output = await app.get_blocks().process_api(
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/gradio/blocks.py", line 2146, in process_api
result = await self.call_function(
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/gradio/blocks.py", line 1664, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2470, in run_sync_in_worker_thread
return await future
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 967, in run
result = context.run(func, *args)
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/gradio/utils.py", line 884, in wrapper
response = f(*args, **kwargs)
File "/mnt/d/zcc/PythonProject/Hunyuan3D-2/gradio_app.py", line 290, in generation_all
textured_mesh = texgen_worker(mesh, image)
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/mnt/d/zcc/PythonProject/Hunyuan3D-2/hy3dgen/texgen/pipelines.py", line 250, in call
multiviews = self.models['multiview_model'](images_prompt, normal_maps + position_maps, camera_info)
File "/mnt/d/zcc/PythonProject/Hunyuan3D-2/hy3dgen/texgen/utils/multiview_utils.py", line 87, in call
mvd_image = self.pipeline(input_images, num_inference_steps=30, **kwargs).images
File "/home/chuxiaoyu/anaconda3/envs/512/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/chuxiaoyu/.cache/huggingface/modules/diffusers_modules/local/pipeline.py", line 364, in call
latents: torch.Tensor = self.denoise(
File "/home/chuxiaoyu/.cache/huggingface/modules/diffusers_modules/local/pipeline.py", line 583, in denoise
prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument tensors in method wrapper_CUDA_cat)

[hadariru]

same problem here!