Error during generation #2
Description
When trying to generate on 4k model, at moment of image output have error:
Loading pipeline components...: 100%|██████████████████████████████████████████████████| 3/3 [00:00<00:00, 1503.33it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 11/11 [00:06<00:00, 1.63it/s]
Traceback (most recent call last):
File "D:\Forge\system\python\lib\site-packages\gradio\queueing.py", line 536, in process_events
response = await route_utils.call_process_api(
File "D:\Forge\system\python\lib\site-packages\gradio\route_utils.py", line 285, in call_process_api
output = await app.get_blocks().process_api(
File "D:\Forge\system\python\lib\site-packages\gradio\blocks.py", line 1923, in process_api
result = await self.call_function(
File "D:\Forge\system\python\lib\site-packages\gradio\blocks.py", line 1508, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "D:\Forge\system\python\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "D:\Forge\system\python\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "D:\Forge\system\python\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "D:\Forge\system\python\lib\site-packages\gradio\utils.py", line 818, in wrapper
response = f(*args, **kwargs)
File "D:\Forge\webui\extensions\Sana-for-webUI\scripts\sana_diffusers.py", line 432, in predict
image = SanaStorage.pipeTR.vae.decode(latent / SanaStorage.pipeTR.vae.config.scaling_factor, return_dict=False)[0]
File "D:\Forge\system\python\lib\site-packages\diffusers\utils\accelerate_utils.py", line 46, in wrapper
return method(self, *args, **kwargs)
File "D:\Forge\system\python\lib\site-packages\diffusers\models\autoencoders\autoencoder_dc.py", line 603, in decode
decoded = self._decode(z)
File "D:\Forge\system\python\lib\site-packages\diffusers\models\autoencoders\autoencoder_dc.py", line 577, in _decode
if self.use_tiling and (width > self.tile_latent_min_width or height > self.tile_latent_min_height):
File "D:\Forge\system\python\lib\site-packages\diffusers\models\modeling_utils.py", line 173, in getattr
return super().getattr(name)
File "D:\Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1729, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")
AttributeError: 'AutoencoderDC' object has no attribute 'tile_latent_min_width'
Diffusers 0.32.0 and accelerator 0.26.0 in requirements installed. 1024 model work well.