diff --git a/multimodal/diffusion/stable-diffusion/training/IMG/res.png b/multimodal/diffusion/stable-diffusion/training/IMG/res.png
new file mode 100644
index 0000000000000000000000000000000000000000..28855d8cc45f2d9aa76ed63815184314cf62efb4
Binary files /dev/null and b/multimodal/diffusion/stable-diffusion/training/IMG/res.png differ
diff --git a/multimodal/diffusion/stable-diffusion/training/README.md b/multimodal/diffusion/stable-diffusion/training/README.md
index 5692785588a419aca16bf35a0591df54bb57464c..89f70e6fe62d7a9899af775a0ba2b9306758039b 100755
--- a/multimodal/diffusion/stable-diffusion/training/README.md
+++ b/multimodal/diffusion/stable-diffusion/training/README.md
@@ -11,16 +11,7 @@ Stable Diffusion is a text-to-image latent diffusion model created by the resear
 pip3 install -r requirements.txt
 ```
 
-###  Download
-
-```bash
-$ wget http://10.150.9.95/swapp/datasets/multimodal/stable_diffusion/pokemon-images.zip
-$ unzip pokemon-images.zip
-$ wget http://10.150.9.95/swapp/pretrained/multimodal/stable-diffusion/stable-diffusion-v1-4.zip
-$ unzip stable-diffusion-v1-4.zip
-```
-
-## Train
+## train
 
 ### step 1   使用accelerate初始化训练环境
 
@@ -42,7 +33,22 @@ multi-gpu
 ### step 2  开始训练
 
 ```bash
-accelerate launch --mixed_precision="fp16" train_text_to_image.py  --pretrained_model_name_or_path=./stable-diffusion-v1-4  --use_ema  --resolution=512 --center_crop --random_flip  --train_batch_size=1  --gradient_accumulation_steps=4  --gradient_checkpointing  --max_train_steps=15000  --learning_rate=1e-05  --max_grad_norm=1  --lr_scheduler="constant" --lr_warmup_steps=0  --output_dir="sd-pokemon-model"  --caption_column 'additional_feature' --train_data_dir pokemon-images/datasets/images/train
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export dataset_name="lambdalabs/pokemon-blip-captions"
+
+accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --dataset_name=$dataset_name \
+  --use_ema \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=4 \
+  --gradient_checkpointing \
+  --max_train_steps=15000 \
+  --learning_rate=1e-05 \
+  --max_grad_norm=1 \
+  --lr_scheduler="constant" --lr_warmup_steps=0 \
+  --output_dir="sd-pokemon-model" 
 ```
 
 ## Test
@@ -50,6 +56,5 @@ accelerate launch --mixed_precision="fp16" train_text_to_image.py  --pretrained_
 python3 test.py
 ```
 prompt:A pokemon with green eyes and red legs   
-
-## Result
-![image](IMG/pokemon.png)
+result:   
+![image](IMG/res.png)