# AttributeError: 'NoneType' object has no attribute 'tokenize'

**URL:** <https://discuss.huggingface.co/t/attributeerror-nonetype-object-has-no-attribute-tokenize/68249>\
**Category:** 🧨 Diffusers\
**Created:** [January 7, 2024, 1:53pm UTC](https://discuss.huggingface.co/t/attributeerror-nonetype-object-has-no-attribute-tokenize/68249 "2024-01-07T13:53:34Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![notsk007](https://avatars.discourse-cdn.com/v4/letter/n/9fc348/32.png) [@notsk007](https://discuss.huggingface.co/u/notsk007)\
**Post date:** [January 7, 2024, 1:53pm UTC](https://discuss.huggingface.co/t/attributeerror-nonetype-object-has-no-attribute-tokenize/68249/1 "2024-01-07T13:53:34Z")

</div>

So i’m getting this error (AttributeError: ‘NoneType’ object has no attribute ‘tokenize’) with some models, any direction towards solving this problem will be appreciated, ty. Here is my code below

#@title #Install Dependencies

# Install the required files and import modules

!pip install -q --upgrade huggingface\_hub

!pip install -q diffusers==0.25.0 accelerate omegaconf xformers transformers gradio mediapy scipy ftfy torchsde k-diffusion fastapi==0.103.2

import mediapy as media

import random

import sys

import torch

import os

from diffusers import DiffusionPipeline

from diffusers.models.attention\_processor import AttnProcessor2\_0

from diffusers import StableDiffusionXLPipeline, AutoencoderKL, DPMSolverMultistepScheduler

from IPython.display import clear\_output

from diffusers import StableDiffusionKDiffusionPipeline

clear\_output()

#@title #Download & Load Model

# Load model from diffusers

model = “digiplay/RealEpicMajicRevolution\_v1” # @param [“digiplay/Realisian\_v5”, “SG161222/Realistic\_Vision\_V6.0\_B1\_noVAE”, “segmind/SSD-1B”, “digiplay/RealEpicMajicRevolution\_v1”, “imagepipeline/Realities-Edge-XL”, “stablediffusionapi/realisian111”] {type:“string”}

pipe = StableDiffusionXLPipeline.from\_pretrained(  
model,  
torch\_dtype=torch.float16,  
variant=“fp16”,  
use\_safetensors=True,  
requires\_safety\_checker=None,  
)  
pipe.scheduler = DPMSolverMultistepScheduler.from\_config(pipe.scheduler.config, use\_karras\_sigmas=True, algorithm\_type=“dpmsolver++”)

# Load it to GPU

pipe = pipe.to(‘cuda’)

#@title #Diffusers UI

# Define every compunent

prompt = “cute dog playing in field” # @param {type:“string”}  
negative\_prompt = “bad anatomy, bad face details, low quality, unrealistic, 3d, anime” # @param {type:“string”}  
num\_inference\_steps = 20 # @param {type:“slider”, def:10, min:1, max:100}  
selected\_resolution = 400, 700 # @param [“1600, 900”,“1280, 720”,“700, 400”,“500, 200”,“200, 500”,“400, 700”,“720, 1280”,“900, 1600”,“512, 512”,“768, 768”,“1024, 1024”] {type:“raw”}  
guidance\_scale = 5 # @param {type:“slider”, def:5, min:0, max:10}  
seed\_input = “1735499402575024878” #@param {type: “string”}  
requires\_safety\_checker = None  
pipe.safety\_checker = None

# Seed randomizer function

if seed\_input == “”:  
seed = random.randint(0, sys.maxsize)  
else:  
try:  
seed = int(seed\_input)  
except ValueError:  
print(“Invalid input. Please enter a valid number.”)  
seed = None

print(“Seed:”, seed)

# Optimizations

pipe.enable\_xformers\_memory\_efficient\_attention()

# Image generation function

images = pipe(  
prompt = prompt,  
negative\_prompt = negative\_prompt,  
guidance\_scale = guidance\_scale,  
num\_inference\_steps = num\_inference\_steps,  
width = selected\_resolution[0] - selected\_resolution[0] % 8,  
height = selected\_resolution[1] - selected\_resolution[1] % 8,  
use\_karras\_sigmas=True,  
generator = torch.Generator(“cuda”).manual\_seed(seed),  
).images

# Show image

media.show\_images(images)  
images[0].save(“output.jpg”)

And My Diffusers Env is below

- `diffusers` version: 0.25.0
- Platform: Linux-6.1.58±x86\_64-with-glibc2.35
- Python version: 3.10.12
- PyTorch version (GPU?): 2.1.2+cu121 (True)
- Huggingface\_hub version: 0.20.2
- Transformers version: 4.35.2
- Accelerate version: 0.25.0
- xFormers version: 0.0.23.post1
- Using GPU in script?: YES
- Using distributed or parallel set-up in script?: