added more md for UI

README.md

@@ -23,7 +23,7 @@ Here are some basic things you should know about it.
 >> The beauty of this process is to integrate with a prompt gpt gave you and slowly start to change it's features on the images based on what you have seen in the previous images, you can simply ask GPT what details to alter and setting but while still mainting the same character looks the diffusor made with the prompt or the style, and slowly but surely you start to get a fully custom image, of what you created in your head help with with both AI's.
 
 Here are key notes in understanding the parameters on the stable diffuser:
-* **Inferece Steps**: These are the number of steps the model will regenerate the image. It starts with a very noisy image from the prompt, and regenerates the image with removing noise by each steps. SO the more steps, the more noise will be removed. However, High steps leads to slow generation but higher quality images.
+* **Inferece Steps**: These are the number of steps the model will regenerate the image. It starts with a very noisy image from the prompt, and regenerates the image with removing noise by each steps. SO the more steps, the more noise will be removed. However, High steps leads to slow generation but higher quality images and lower steps leads to faster generation but often lower quality images, I'd recommend to leave the steps at 40.
 * **High Noise Fraction**: The amount of noise added to the image during the initial stages of the diffusion process. A higher noise forces the model to learn patterns associated with the prompt than as much with the image due to the amount of noise during diffusing. Lower Noise makes the model have more versatility and creativity with the image but can make it unaligned with the prompt often due to overfitting from faster convergence. With less noise the model captures less features of the prompt, resulting in images that are less aligned with the prompt.
 
 My rule of thumb with the parameters are to leave them at there default values unless you see the model needs more creativity in creating that specific image from the prompt. When more creativity is needed I just place the High Noise Fraction between 6-7 but to be honest you can play around these cause it's often random, the lowest I would go would be 4 but only if the model really needs creativity. I personally never place the model higher the 8.0 because i feel it lacks a bit creativity in creating and tries to emulate exactly what the prompt gives that it actually deviates from what the prompt was saying.

app.py

@@ -22,6 +22,7 @@ DESCRIPTION = '''
 <div>
 <h1 style="text-align: center;">Chimera Image Generation</h1>
 <p style="text-align: center;">This contains a Stable Diffusor from <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0"><b>stabilityai/stable-diffusion-xl-base-1.0</b></a></p>
+<p style="text-align: center;">For Instructions on how to use the models <a href="https://huggingface.co/spaces/sandz7/chimera/blob/main/README.md"><b>view this</b></a></p>
 </div>
 '''
 # DESCRIPTION = '''
@@ -227,6 +228,7 @@ with gr.Blocks(fill_height=True) as demo:
 <div>
 <h1 style="text-align: center;">Chimera Text Generation</h1>
 <p style="text-align: center;">This contains a Generative LLM from <a href="https://openai.com/"><b>Open AI</b></a> called GPT-3.5-Turbo and Vision.</p>
+<p style="text-align: center;">For Instructions on how to use the models <a href="https://huggingface.co/spaces/sandz7/chimera/blob/main/README.md"><b>view this</b></a></p>
 </div>
 ''')
             chat = gr.ChatInterface(fn=bot_comms,