Prompt
a skyline view of a futuristic maritime village floating above ground, in the clouds, large human robotic structure in the far background, towering skyscrapers, day time lighting, orange teal color scheme, epic scale
Base model
Fine-tuned model
Prompt
a three fourth perspective waist up portrait view of a young woman with messy long blonde hair and light purple eyes, perfect face, looking at viewer with a closed mouth smile, wearing loose black dress, a faded pink simple background during golden hour
Base model
Fine-tuned model
Prompt
a man in his late 30s to early 40s, rendered in a dark, moody style, The subject is depicted from the shoulders up, facing the viewer directly, He has a full, thick beard and mustache, which is dark and well-groomed, with a few strands of gray, His hair is short and neatly combed, with a few strands falling over his forehead, His eyes are dark and piercing, with a slight hint of sadness or introspection,
Base model
Fine-tuned model
Prompt
a sci-fi venetian town near the water
Base model
Fine-tuned model
Purpose: Understand the difference between fine-tuning SD1.5/SDXL and Stable Diffusion 3 Medium/Large (SD3.5M/L) and enable more users to fine-tune on both models.
Hello! My name is Yeo Wang, and I’m a Generative Media Solutions Engineer at Stability AI and freelance 2D/3D concept designer. You might have seen some of my videos on YouTube or know about me through the community (Github).
The previous fine-tuning guide regarding Stable Diffusion 3 Medium was also written by me (with a slight allusion to this new 3.5 family of models). I’ll be building off the information in that post, so if you’ve gone through it before, it will make this much easier as I’ll be using similar techniques from there.