Vampire Style
Vampire Style v2.0
I've created a new model on Stable Diffusion 1.5 for generating vampire portraits! Using a variety of sources such as movies, novels, video games, and cosplay photos, I've trained the model to produce images with all the classic vampire features like fangs and glowing eyes. While some images may require a bit of cleanup or more detailed prompts, you can expect to get great results with just basic prompts using the trigger word "OOKZA Vampire Style", eg. "OOKZA Vampire Style portrait of (Sarah Michelle Gellar) as a Vampire, dramatic lighting, intricate, gothic, highly detailed, digital painting, trending on artstation, concept art, smooth, sharp focus, illustration, 8k, photo realistic, masterpiece." This model also works quite well with IMG2IMG to suppliment your existing vampire portraits with gaping, hissing vampire mouths.
What is Vampire Style?
Vampire Style is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user onlyonekenobi79. Derived from the powerful Stable Diffusion (SD 1.5) model, Vampire Style has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Vampire Style is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as horror, monsters, undead.
With a rating of 5 and over 3 ratings, Vampire Style is a popular choice among users for generating high-quality images from text prompts.
Can I download Vampire Style?
Yes! You can download the latest version of Vampire Style from here.
How to use Vampire Style?
To use Vampire Style, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Vampire Style, check out our crash course in AI image generation.
Popularity
Info
Latest version (Vampire Style v2.0): 1 File
About this version: Vampire Style v2.0
This is a new version of the Vampire style model from scratch using a different Dreambooth colab. The results are improved from version 1.0 and in this version the Trigger words are OOKZAVampire Style (two words and not three as in the previous version). Certain vampire themed terms such as fangs, canine teeth, sharp teeth, hissing, screaming, snarling, smiling, baring teeth, exposed teeth will improve or change the output depending on your requirements.
I've found that keeping the CFG scale between 7-12 generally gives the best results for good looking fangs with higher CFGs seemingly creating an "oversharpened" look on them, but higher CFG scale will also start drawing additional horror themed elements such as blood drips and splashes. One might composite different versions of the render to get the best results for good looking teeth combined with blood drips and splashes.
EULER A with 20-40 steps and DPM++2S a Karras, and DPM++ 2M Karras with 30+ steps seem to provide decent image quality.
