GlitchHunter / README.md
alvdansen's picture
initial commit
c7d9b4b verified
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
A vibrant, 3D like whimsical creature shaman world, morphed with glowing
orbs and intricate patterns, exuding an enchanting, otherworldly charm
amidst a colorful backdrop. [GlitchHunter]
output:
url: >-
images/1642-A_vibrant_3D_like_whimsical_creature_sh-Fluxflux1-dev-fp8-1477173756.png
- text: 3D mantis eating cybernetic pizza on the vibrant beach, [GlitchHunter]
output:
url: >-
images/1655-3D_mantis_eating_cybernetic_pizza_on_the-Fluxflux1-dev-fp8-804977402.png
- text: mysterious 3D cat in neo-tokyo, [GlitchHunter]
output:
url: >-
images/1649-mysterious_3D_cat_in_neo-tokyo-Fluxflux1-dev-fp8-2079831861.png
- text: abstract comic like whimsical mysterious Cthulhu monster, [GlitchHunter]
output:
url: >-
images/1703-abstract_comic_like_whimsical_mysterious-Fluxflux1-dev-fp8-123641784.png
- text: abstract comic like alien from space, [GlitchHunter]
output:
url: >-
images/1704-abstract_comic_like_alien_from_space-Fluxflux1-dev-fp8-1230555433.png
- text: >-
A glowing, bubbly neon and otherworldly creature stands amidst mystical
swampy flora, cradling a luminescent orb, surrounded by swirling colors and
ethereal energy, [GlitchHunter]
output:
url: >-
images/1716-A_glowing_bubbly_neon_and_otherworldly-Fluxflux1-dev-fp8-250006613.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: '[GlitchHunter]'
license: cc0-1.0
---
# GlitchHunter
<Gallery />
## Model description
**Creator:** [KoshiMazaki](https:&#x2F;&#x2F;glif.app&#x2F;@Koshi)
**Style:**GlitchHunter is a Flux dev LoRA trained on Koshi&#39;s outputs from MJ and SDXL, focusing on creating erratic, abstract, and highly stylised characters. It merges glitch art with vibrant, abstract, and comic elements, producing a unique fusion of these styles. Trained on multiple aesthetics, it blends them seamlessly into new forms.
While it leans toward a neon cyberpunk comic aesthetic, GlitchHunter also adapts well to other subjects. For broader creativity, you can experiment with different colour schemes and environments beyond the neon cyberpunk theme. The model generates a mix of the following styles, letting you hunt for glitches and style morphs:
- 2D abstract comic
- 2.5D toon shader-like visuals
- 3D designer toy-inspired mecha sculptures
**Click here to try it on Glif:**
[![Try it on Glif!](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;635dd6cd4fabde0df74aeae6&#x2F;I2E-g7OdeA2ST8zd6zark.jpeg)](https:&#x2F;&#x2F;glif.app&#x2F;@Koshi&#x2F;glifs&#x2F;cm16e0vir0005dlu6lp9oufai)
*This LoRA is a part of the Glif Loradex Trainer project. The goal of the project is to explore different training techniques together, create and release opensource LoRAs, and fill the world with more art. This project is sponsored by [Glif](https:&amp;#x2F;&amp;#x2F;glif.app&amp;#x2F;), offering free early access to Flux Dev training on the Glif Discord.*
*All models in the Loradex Trainer program are released under the BFL Flux Dev license. Attribution for the original LoRA creator is always appreciated!*
## Trigger words
You should use `[GlitchHunter]` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/glif/GlitchHunter/tree/main) them in the Files & versions tab.