diff --git a/requirements.txt b/requirements.txt
index 01bcfb8..5c11e82 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,3 @@
 accelerate
-diffusers
\ No newline at end of file
+diffusers>=0.28.0
+Pillow
\ No newline at end of file
diff --git a/stabledelight/controlnetvae.py b/stabledelight/controlnetvae.py
index 3903066..0a58931 100644
--- a/stabledelight/controlnetvae.py
+++ b/stabledelight/controlnetvae.py
@@ -16,7 +16,6 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 
 import torch
 
-
 from diffusers.models.controlnet import ControlNetOutput
 from diffusers.models import ControlNetModel
 
diff --git a/stabledelight/pipeline_yoso_delight.py b/stabledelight/pipeline_yoso_delight.py
index f2bbe33..2d727fe 100644
--- a/stabledelight/pipeline_yoso_delight.py
+++ b/stabledelight/pipeline_yoso_delight.py
@@ -100,10 +100,6 @@ class YosoDelightPipeline():
     Args:
         vae ([`AutoencoderKL`]):
             Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
-        text_encoder ([`~transformers.CLIPTextModel`]):
-            Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
-        tokenizer ([`~transformers.CLIPTokenizer`]):
-            A `CLIPTokenizer` to tokenize text.
         unet ([`UNet2DConditionModel`]):
             A `UNet2DConditionModel` to denoise the encoded image latents.
         controlnet ([`ControlNetModel`] or `List[ControlNetModel]`):