Error doing Textdiffuser2 inpainting demo

[HERIUN]

Describe the bug
Model I am using : Textdiffuser2

The problem arises when using:

• the official example scripts: (give details below)
• my own modified scripts: (give details below)

A clear and concise description of what the bug is.

demo_textdiffuser2_inpainting_full.py

doesn't work. huggingface link not exists.

and

def get_conversation_template()
m1_tokenizer, m1_model no exists

[Ace0001]

Hi, have you solved the problem?

[ec-lp]

Hi. I am having similar problem. Has anyone got a simple example that works, not necessarily using gradio?

[HERIUN]

I didn't try, but i will... edit demo_textdiffuser2_inpainting_full.py

add

from fastchat.model import get_conversation_template
from transformers import CLIPTextModel, CLIPTokenizer, AutoTokenizer, AutoModelForCausalLM

m1_model_path = "JingyeChen22/textdiffuser2_layout_planner"
cache_dir = "model_cache"
local_files_only = True  # set to True if the models are saved in cache_dir
m1_tokenizer = AutoTokenizer.from_pretrained(
            m1_model_path,
            use_fast=False,
            cache_dir=cache_dir,
            local_files_only=local_files_only,
        )
m1_model = AutoModelForCausalLM.from_pretrained(
            m1_model_path,
            torch_dtype=torch.float16,
            low_cpu_mem_usage=True,
            cache_dir=cache_dir,
            local_files_only=local_files_only,
        ).cuda()

replace
runwayml/stable-diffusion-v1-5 -> stable-diffusion-v1-5/stable-diffusion-v1-5

and font path edit
./Arial.ttf -> ./assets/arial.ttf