AttributeError: 'RegionDiffusion' object has no attribute 'tokenizer'

[jasoncow007]

Traceback (most recent call last):
File "D:\sd-webui-aki-v4\py310\lib\site-packages\gradio\routes.py", line 488, in run_predict
output = await app.get_blocks().process_api(
File "D:\sd-webui-aki-v4\py310\lib\site-packages\gradio\blocks.py", line 1431, in process_api
result = await self.call_function(
File "D:\sd-webui-aki-v4\py310\lib\site-packages\gradio\blocks.py", line 1103, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\sd-webui-aki-v4\py310\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "D:\sd-webui-aki-v4\py310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "D:\sd-webui-aki-v4\py310\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "D:\sd-webui-aki-v4\py310\lib\site-packages\gradio\utils.py", line 707, in wrapper
response = f(*args, **kwargs)
File "D:\sd-webui-aki-v4\extensions\sd-webui-rich-text\scripts\rich_text_on_tab.py", line 123, in generate
region_text_prompts, region_target_token_ids, base_tokens = get_region_diffusion_input(
File "D:\sd-webui-aki-v4\extensions\sd-webui-rich-text\scripts\models\utils\richtext_utils.py", line 146, in get_region_diffusion_input
base_tokens = model.tokenizer._tokenize(base_text_prompt)
File "D:\sd-webui-aki-v4\py310\lib\site-packages\torch\nn\modules\module.py", line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'RegionDiffusion' object has no attribute 'tokenizer'

[songweige]

I think this might be related to the failure of loading the model. Did you see multiple lines of "[INFO] loading stable diffusion"(

sd-webui-rich-text/scripts/models/region_diffusion.py

Line 28 in a02b874

print(f'[INFO] loading stable diffusion {model_id} ... attempt {load_attemp}')

)? I have added some code to print more information about errors. Could you try to update the extension again and see if there something new?

[jasoncow007]

it didn't download the model automaticly,,,,,,what's the path of the model

[INFO] loading stable diffusion...
[INFO] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 0
[ERROR] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 0 failed with error runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json.
[INFO] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 1
[ERROR] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 1 failed with error runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json.
[INFO] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 2
[ERROR] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 2 failed with error runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json.
[INFO] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 3
[ERROR] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 3 failed with error runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json.
[INFO] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 4
[ERROR] loading stable diffusion runwayml/stable-diffusion-v1-5 ... attempt 4 failed with error runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json.
[INFO] loaded stable diffusion!

[songweige]

It is supposed to download the checkpoint automatically from https://huggingface.co/runwayml/stable-diffusion-v1-5. I guess there might be some incomplete downloading. Could you check the folder .cache/huggingface/diffusers/' and delete the cache of the checkpoint and try again? Also, do you have a different version of diffusers other than 0.18.2`.?