Update README.md

README.md

@@ -67,42 +67,57 @@ license_name: flux-1-dev-non-commercial-license
 license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
 ---
 <Gallery />
-
 ‎
 # **BLAZE.1 PORTRAIT**
 
-Blaze.1 Portrait is a flux-based adapter capable of generating high-quality realistic/realism-based super-portraits. The image training included 72 variations, with 1080 total images for each variation and 15 images per variation. The images used in the training were 14-bit raw Camera Uncompressed Format (CUF). For more details, refer to the training and data curation documentation, and training parameters.
+Blaze.1 Portrait is a flux-based adapter designed to generate high-quality, realism-driven super-portraits. This advanced model underwent rigorous training using a diverse set of images to ensure exceptional output in portrait generation. With 72 variations and a total of 1080 images per variation, the training process involved meticulous curation and processing of 14-bit raw Camera Uncompressed Format (CUF) images. For comprehensive insights, refer to the detailed documentation on training procedures, data curation, and parameter optimization.
 
 # **Image Processing Parameters**  
 
-| Parameter                 | Value                                   | Parameter                 | Value                        |
+| **Parameter**             | **Value**                               | **Parameter**             | **Value**                    |
 |---------------------------|-----------------------------------------|---------------------------|------------------------------|
-| LR Scheduler              | constant                                | Noise Offset              | 0.03                         |
+| LR Scheduler              | Constant                                | Noise Offset              | 0.03                         |
 | Optimizer                 | AdamW                                   | Multires Noise Discount   | 0.1                          |
 | Network Dim               | 64                                      | Multires Noise Iterations | 10                           |
-| Network Alpha             | 32                                      | **Repeat & Steps**        | **<span style="color:orangered">30</span> <span style="color:orangered">&</span> <span style="color:orangered">38,000</span>** |
+| Network Alpha             | 32                                      | **Repeat & Steps**        | **<span style="color:orangered">30 & 38,000</span>**|
 | **Epoch**                 | **<span style="color:orangered">45</span>** | Save Every N Epochs       | 1                            |
 
-The Model Underwent an Overall Training of 1080 Images, with a Total of 1100 Images per Repetition, and was Trained for 4 Epochs on Each Set, with 38,000 Steps
+- The model was trained with an overall image count of **1080 images**, repeated across variations to create a total dataset of **1100 images per repetition**.
+- Training was conducted for **4 epochs per set**, resulting in a cumulative total of **38,000 steps**.
 
 # **Dataset Details**
 
-- The model datasets were prepared with reference to realistic images. The images were trained on batches of sets of smaller adapter versions. Hi-resolution images were generated from the adapters and subsequently used for training. Even before training, the images were highly upscaled using an upscaler to increase pixel clarity.
+- The dataset consists of highly realistic images, meticulously curated for optimal model performance. Smaller adapter versions were initially trained on batches, and high-resolution images were later generated from these adapters for further training.
+- Pre-training upscaling techniques were employed to enhance pixel clarity, ensuring superior image fidelity during model inference.
+- Image compression details:
+  - **Minimum compression:** 1.4 MB  
+  - **Maximum compression:** 10.1 MB  
+  - **Average compression:** 3.2 MB
+
+# **Training Infrastructure**
+
+Blaze.1 Portrait was trained using state-of-the-art hardware:
 
-- The image dataset has a minimum compression of 1.4 MB, a maximum compression of 10.1 MB, and an average compression of 3.2 MB.
+- **GPU Configuration:** NVIDIA A100 SXM (2x)
+- **vCPU:** 32 cores
+- **VRAM:** 160 GB
+- **RAM:** 250 GB
+- **Disk Space:** 400 GB
+- **Network Memory:** High-speed interconnects for efficient data transfer
 
-# **Training Details**
+# **Training Runtime**
+- Total machine runtime: **<span style="color:orangered">8 hours 14 minutes</span>**
 
-Blaze.1 Portrait was trained on NVIDIA A100 SXM (2x) with 32 vCPUs, 160 GB of VRAM, 250 GB of RAM, 400 GB of disk space, and network memory
+# **Trigger Words**
 
-- Training Hours (Machine Runtime): **<span style="color:orangered">8 hours 14 minutes</span>**
- 
-# **Trigger words**
+To generate images using Blaze.1 Portrait, utilize the trigger phrase:
 
-You should use **<span style="color:orangered">b1 portrait</span>** to trigger the image generation.
+- **<span style="color:orangered">b1 portrait</span>**
+- 
+Incorporating this trigger in your prompts ensures optimal model performance and high-quality portrait generation.
 
-# **Download model**
+# **Download Model**
 
-Weights for this model are available in Safetensors format.
+Weights for Blaze.1 Portrait are available in Safetensors format. You can download them from the Files & Versions tab using the link below:
 
-[Download](/strangerzonehf/Blaze.1-Portrait/tree/main) them in the Files & versions tab.
+[**Download Blaze.1 Portrait Weights**](/strangerzonehf/Blaze.1-Portrait/tree/main)