CUDA out of memory

[matrix4767]

Looks like this extension can't be ran on anything but high memory video cards...

G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\region_diffusion.py:203: FutureWarning: Accessing config attribute in_channels directly via 'UNet2DConditionModel' object attribute is deprecated. Please access 'in_channels' over 'UNet2DConditionModel's config object instead, e.g. 'unet.config.in_channels'. (text_embeddings.shape[0] // 2, self.unet.in_channels, height // 8, width // 8), device=self.device) Traceback (most recent call last): File "G:\stable-webui\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "G:\stable-webui\venv\lib\site-packages\gradio\blocks.py", line 1431, in process_api result = await self.call_function( File "G:\stable-webui\venv\lib\site-packages\gradio\blocks.py", line 1103, in call_function prediction = await anyio.to_thread.run_sync( File "G:\stable-webui\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "G:\stable-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "G:\stable-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 807, in run result = context.run(func, *args) File "G:\stable-webui\venv\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\rich_text_on_tab.py", line 146, in generate plain_img = model.produce_attn_maps([base_text_prompt], [negative_text], File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\region_diffusion.py", line 215, in produce_attn_maps noise_pred = self.unet( File "G:\stable-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\unet_2d_condition.py", line 959, in forward sample = upsample_block( File "G:\stable-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\unet_2d_blocks.py", line 2143, in forward hidden_states = attn( File "G:\stable-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\transformer_2d.py", line 291, in forward hidden_states = block( File "G:\stable-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\attention.py", line 155, in forward attn_output, _ = self.attn1( File "G:\stable-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1538, in _call_impl result = forward_call(*args, **kwargs) File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\attention_processor.py", line 330, in forward return self.processor( File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\attention_processor.py", line 1159, in call attention_probs = attn.get_attention_scores(query, key, attention_mask, attn_weights=attn_weights) File "G:\stable-webui\extensions\sd-webui-rich-text\scripts\models\attention_processor.py", line 401, in get_attention_scores attention_probs = attention_scores.softmax(dim=-1) torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1024.00 MiB (GPU 0; 12.00 GiB total capacity; 8.67 GiB already allocated; 0 bytes free; 9.76 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF