diff --git a/README.md b/README.md
index e7cf7cd..8996cb6 100644
--- a/README.md
+++ b/README.md
@@ -300,16 +300,53 @@ This mirrors how the resources are placed in the [HuggingFace Repo](https://hugg
 
 ### LoRA
 
-MFLUX support loading precomputed [LoRA](https://huggingface.co/docs/diffusers/en/training/lora) weights (training support is coming soon). 
-By pointing out 
+MFLUX support loading trained [LoRA](https://huggingface.co/docs/diffusers/en/training/lora) adapters (actual training support is coming).
+
+The following example [The_Hound](https://huggingface.co/TheLastBen/The_Hound) LoRA from [@TheLastBen](https://github.com/TheLastBen): 
+
+```
+python main.py --prompt "sandor clegane" --model dev --steps 20 --seed 43 -q 8 --lora-paths "sandor_clegane_single_layer.safetensors"
+```
+
+![image](src/flux_1/assets/lora1.jpg)
+---
+
+The following example is [Flux_1_Dev_LoRA_Paper-Cutout-Style](https://huggingface.co/Norod78/Flux_1_Dev_LoRA_Paper-Cutout-Style) LoRA from [@Norod78](https://github.com/TheLastBen):
+
+```
+python main.py --prompt "pikachu, Paper Cutout Style" --model schnell --steps 4 --seed 43 -q 8 --lora-paths "Flux_1_Dev_LoRA_Paper-Cutout-Style.safetensors"
+```
+![image](src/flux_1/assets/lora2.jpg)
+
+*Note that LoRA trained weights are typically trained with a **trigger word or phrase**. For example, in the latter case, the sentence should include the phrase **"Paper Cutout Style"**.*
+
+*Also note that the same LoRA weights can work well with both the `schnell` and `dev` models. Refer to the original LoRA repository to see what mode it was trained for.*
+
+#### Multi-LoRA
+
+Multiple LoRAs can be sent in to combine the effects of the individual adapters. The following example combines both of the above LoRAs:
+
+```
+python main.py \
+--prompt "sandor clegane in a forest, Paper Cutout Style" \ 
+--model dev \
+--steps 20 \
+--seed 43 \
+--lora-paths sandor.safetensors paper.safetensors \ 
+--lora-scales 1.0 1.0 -q 8 \
+```
+![image](src/flux_1/assets/lora3.jpg)
+
+Just to see the difference, this image displays the four cases: One of having both adapters fully active, partially active and no LoRA at all. 
+The example above also show the usage of `--lora-scales` flag. 
 
 ### Current limitations
 
 - Images are generated one by one.
 - Negative prompts not supported.
+- LoRA weights are only supported for the transformer part of the network.
 
 ### TODO
 
-- [ ] LoRA adapters
 - [ ] LoRA fine-tuning
 - [ ] Frontend support (Gradio/Streamlit/Other?)
\ No newline at end of file
diff --git a/src/flux_1/assets/lora1.jpg b/src/flux_1/assets/lora1.jpg
new file mode 100644
index 0000000..46188d4
Binary files /dev/null and b/src/flux_1/assets/lora1.jpg differ
diff --git a/src/flux_1/assets/lora2.jpg b/src/flux_1/assets/lora2.jpg
new file mode 100644
index 0000000..b317be0
Binary files /dev/null and b/src/flux_1/assets/lora2.jpg differ
diff --git a/src/flux_1/assets/lora3.jpg b/src/flux_1/assets/lora3.jpg
new file mode 100644
index 0000000..f83edb6
Binary files /dev/null and b/src/flux_1/assets/lora3.jpg differ