driftjohnson
over 2 years ago

How this Model was made: [timelapse]

This Model was created by glitching some images created with recent djz models. Audacity was used, you can see the process above.

theOvercomer8s contrast fix or High Key LORA was used in some examples (link at the bottom)

As shown below, using light prompts or naked tokens alone, then choosing a low denoise on the hi res pass, we can achieve these beautifully stylized Glitched images using this model.
A LORA retrain will arrive in time. Thanks for stopping by ;)

prompt: "(GlitchStick:1)"

This model is not limited to Glitched images and can be prompted to produce both Anime and Photorealism, while still retaining some of the interesting hallmarks it was trained on:

examples using Anime / Photo realism:
Prompt: "(GlitchStick:1) anime, pretty woman looks at a giant flower in the sky, anime, digital art, trending on artstation, hd, 8 k, sharp high quality artwork in style of greg rutkowski, concept art, blizzard warcraft artwork, hearthstone card artwork, league of legends artwork, bright colors, blue sky background, red flowers, yellow grass, red leaves, orange sun,red clouds, ocean floor, fighting each"


Prompt: "(GlitchStick:1) photo, pretty woman looks at the camera. she is wearing a white dress with gold accents and has an orange hoodie on her face!!! dramatic lighting cinematic establishing shot extremely high detail post processed underexposed 8k by simon stalenhag paul lehr greg rutkowski surrealism dark monochrome trending 4 k hq sharp focus"


Contrast Fix / High Key by theOvercomer8s
https://civitai.com/models/8765/theovercomer8s-contrast-fix-sd15sd21-768
https://civitai.com/models/9205/to8s-high-key-lora-sd15sd21-768

Read more...

What is djz Glitch Stick?

djz Glitch Stick is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user driftjohnson. Derived from the powerful Stable Diffusion (SD 2.1 768) model, djz Glitch Stick 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 djz Glitch Stick is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, abstract, glitch.

With a rating of 0 and over 0 ratings, djz Glitch Stick is a popular choice among users for generating high-quality images from text prompts.

Can I download djz Glitch Stick?

Yes! You can download the latest version of djz Glitch Stick from here.

How to use djz Glitch Stick?

To use djz Glitch Stick, 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 djz Glitch Stick, check out our crash course in AI image generation.

Download (2.37 GB) Download available on desktop only
You'll need to use a program like A1111 to run this – learn how in our crash course

Popularity

130 30

Info

Base model: SD 2.1 768
Trigger word:

Latest version (V21-768): 1 File

To download these files, please visit this page from a desktop computer.

About this version: V21-768

Although this can be used for Anime or Photorealism, this is intended for producing Glitch Images.

1 Version

djz Glitch Stick V21-768 prompts

Explore the best djz Glitch Stick prompts