---
license: wtfpl
---

Doesn't always work, but gets you a lot closer quickly compared to just trying keywords.

Dataset of 18 images, 3 vectors, batch size of 3, 3 steps gradient accumulation, trained for 500 steps or 250 epochs.


![15196-4029360196-HyperNuke, (((((skull)) shaped cloud))),  volumetric lighting, aerial shot,dblx, vorticity and turbulence, orange glow, explosio.png](https://s3.amazonaws.com/moonup/production/uploads/1671530137257-6312579fc7577b68d90a7646.png)

![15193-2262279174-HyperNuke, (((skull shaped cloud))),  volumetric lighting, aerial shot,dblx, vorticity and turbulence, orange glow, explosion, t.png](https://s3.amazonaws.com/moonup/production/uploads/1671530139199-6312579fc7577b68d90a7646.png)


![15182-3389199702-HyperNuke,  volumetric lighting, aerial shot, vorticity and turbulence, orange glow, explosion, tsar bomba, clouds, desert, vibr.png](https://s3.amazonaws.com/moonup/production/uploads/1671530421685-6312579fc7577b68d90a7646.png)




![15209-3282920038-HyperNuke,   aerial shot,vorticity and turbulence, orange glow, clouds, desert, vibrant, hasselblad, extremely detailed, actionh.png](https://s3.amazonaws.com/moonup/production/uploads/1671530305984-6312579fc7577b68d90a7646.png)