Apply suggestions from code review

Co-authored-by: Aryan <[email protected]>

Author: sayakpaul

examples/control-lora/README.md

@@ -1,8 +1,8 @@
 # Training Control LoRA with Flux
 
-This (experimental) example shows how train Control LoRA with [Flux](https://huggingface.co/black-forest-labs/FLUX.1-dev) to condition it with additional structural controls (like depth maps, poses, etc.). 
+This (experimental) example shows how to train Control LoRAs with [Flux](https://huggingface.co/black-forest-labs/FLUX.1-dev) by conditioning it with additional structural controls (like depth maps, poses, etc.).
 
-We simply expand the input channels of Flux.1 Dev from 64 to 128 to allow for additional inputs and then train a regular LoRA on top of it. To account for the newly added input channels, we additional append a LoRA on the underlying layer (`x_embedder`). Inference, however, is performed with the `FluxControlPipeline`. 
+To incorporate additional condition latents, we expand the input features of Flux.1-Dev from 64 to 128. The first 64 channels correspond to the original input latents to be denoised, while the latter 64 channels correspond to control latents. This expansion happens on the `x_embedder` layer, where the combined latents are projected to the expected feature dimension of rest of the network. Inference is performed using the `FluxControlPipeline`.
 
 > [!NOTE]
 > **Gated model**

examples/control-lora/train_control_flux.py

@@ -188,7 +188,7 @@ def save_model_card(repo_id: str, image_logs=None, base_model=str, repo_folder=N
             img_str += f"![images_{i})](./images_{i}.png)\n"
 
     model_description = f"""
-# controlnet-{repo_id}
+# control-lora-{repo_id}
 
 These are Control weights trained on {base_model} with new type of conditioning.
 {img_str}

examples/control-lora/train_control_lora_flux.py

@@ -224,6 +224,7 @@ def save_model_card(repo_id: str, image_logs=None, base_model=str, repo_folder=N
         "diffusers",
         "control-lora",
         "diffusers-training",
+        "lora",
     ]
     model_card = populate_model_card(model_card, tags=tags)