This is a great work! But the web demo has a problem shown as follows:

[QvQKing]

Traceback (most recent call last): File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/gradio/routes.py", line 437, in run_predict output = await app.get_blocks().process_api( File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/gradio/blocks.py", line 1352, in process_api result = await self.call_function( File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/gradio/blocks.py", line 1093, in call_function prediction = await utils.async_iteration(iterator) File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/gradio/utils.py", line 341, in async_iteration return await iterator.anext() File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/gradio/utils.py", line 334, in anext return await anyio.to_thread.run_sync( File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread return await future File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, *args) File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/gradio/utils.py", line 317, in run_sync_iterator_async return next(iterator) File "/hy-tmp/LLMGA-master/llmga/serve/gradio_web_server.py", line 198, in generation_bot image = pipe(caption,num_inference_steps=num_inference_steps).images[0] File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/hy-tmp/LLMGA-master/llmga/diffusers/pipeline_stable_diffusion_xl_lpw.py", line 903, in call latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0] File "/usr/local/miniconda3/envs/llmga/lib/python3.9/site-packages/diffusers/schedulers/scheduling_euler_discrete.py", line 498, in step pred_original_sample = sample - sigma_hat * model_output RuntimeError: The size of tensor a (9) must match the size of tensor b (4) at non-singleton dimension 1