Update README.md

README.md

@@ -26,21 +26,15 @@ widget:
     url: image_3.png
 ---
 
-<!-- This model card has been generated automatically according to the information the training script had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# SD3 DreamBooth LoRA - AdamLucek/sd3-cube-dreambooth-lora-cube
 
+**Reference Image**
 
-# SD3 DreamBooth LoRA - AdamLucek/sd3-cube-dreambooth-lora-2
-
-<Gallery />
+**Generated Images**
 
 ## Model description
 
-These are AdamLucek/sd3-cube-dreambooth-lora-2 DreamBooth LoRA weights for stabilityai/stable-diffusion-3-medium-diffusers.
-
-The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [SD3 diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sd3.md).
-
-Was LoRA for the text encoder enabled? True.
+These are DreamBooth LoRA weights for [stabilityai/stable-diffusion-3-medium-diffusers](https://huggingface.co/stabilityai/stable-diffusion-3-medium).
 
 ## Trigger words
 
@@ -48,7 +42,7 @@ You should use `A photo of T0K cube` to trigger the image generation.
 
 ## Download model
 
-[Download the *.safetensors LoRA](AdamLucek/sd3-cube-dreambooth-lora-2/tree/main) in the Files & versions tab.
+[Download the pytorch_lora_weights.safetensors LoRA](AdamLucek/sd3-cube-dreambooth-lora-cube/tree/main) in the Files & versions tab.
 
 ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
 
@@ -62,7 +56,7 @@ image = pipeline('A photo of T0K cube on a shelf').images[0]
 
 ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
 
-- **LoRA**: download **[`diffusers_lora_weights.safetensors` here 💾](/AdamLucek/sd3-cube-dreambooth-lora-2/blob/main/diffusers_lora_weights.safetensors)**.
+- **LoRA**: download **[`diffusers_lora_weights.safetensors` here 💾](/AdamLucek/sd3-cube-dreambooth-lora-cube/blob/main/diffusers_lora_weights.safetensors)**.
     - Rename it and place it on your `models/Lora` folder.
     - On AUTOMATIC1111, load the LoRA by adding `<lora:your_new_name:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
 
@@ -72,19 +66,32 @@ For more details, including weighting, merging and fusing LoRAs, check the [docu
 
 Please adhere to the licensing terms as described [here](https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/LICENSE).
 
+## Training details
 
-## Intended uses & limitations
-
-#### How to use
+The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [SD3 diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sd3.md).
 
-```python
-# TODO: add an example code snippet for running this diffusion pipeline
+Script
+```
+accelerate launch train_dreambooth_lora_sd3.py \
+  --pretrained_model_name_or_path="stabilityai/stable-diffusion-3-medium-diffusers"  \
+  --output_dir="lora-trained-sd3-t3" \
+  --dataset_name="AdamLucek/cube-pics-dreambooth" \
+  --mixed_precision="fp16" \
+  --instance_prompt="A photo of T0K cube" \
+  --resolution=1024 \
+  --train_batch_size=16 \
+  --learning_rate=1e-4 \
+  --report_to="wandb" \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --max_train_steps=1000 \
+  --validation_prompt="A photo of T0K cube on a shelf" \
+  --validation_epochs=500 \
+  --seed="420" \
+  --rank=16 \
+  --hub_model_id="sd3-cube-dreambooth-lora-2" \
+  --train_text_encoder \
+  --push_to_hub
 ```
 
-#### Limitations and bias
-
-[TODO: provide examples of latent issues and potential remediations]
-
-## Training details
-
-[TODO: describe the data used to train the model]
+Trained on a single H100