diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/README.md b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/README.md
index 8a2dded6..7082bf6a 100644
--- a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/README.md
+++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/README.md
@@ -14,6 +14,11 @@ brain MRI data. The model is divided into two parts: an autoencoder with a KL-re
into a latent space and a diffusion model that learns to generate conditioned synthetic latent representations. This
model is conditioned on age, sex, the volume of ventricular cerebrospinal fluid, and brain volume normalised for head size.
+
+
+Figure 1 - Synthetic image from the model.
+
+
## **Data**
The model was trained on brain data from 31,740 participants from the UK Biobank [2]. We used high-resolution 3D T1w MRI with voxel size of 1mm3, resulting in volumes with 160 x 224 x 160 voxels
diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/figure_1.png b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/figure_1.png
new file mode 100644
index 00000000..b3bed96a
Binary files /dev/null and b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/figure_1.png differ