Lun's Pony Diffusion Models

Stable Diffusion finetuned on derpibooru
by

V2

This model was finetuned from Stable Diffusion's 1.4 release with batch size 3 and 5e-6 learning rate on a single Radeon Pro W6800 GPU.

Captions use space separated tags. Spaces within tags should be replaced with underscores.

The autoencoder was finetuned for ~120,000 steps before finetuning the rest of the model.

Full finetune release

Global step count in filename doesn't match in the state_dict due to the way I resumed at one point.

TODO: Sample images, release more checkpoints later.

Short finetune / Beta (2022-10-11) Model

This checkpoint was captured after ~26,000 steps (~80,000 images) of training, which took 12 hours. This isn't even a full epoch.

pony s5_starlight unicorn glimmer this_will_end_in_communism scr100 bust mare portrait by=pierogarts female safe looking_at_you solo

This shows that finetuning to a reasonable quality level does not need a huge cluster of expensive datacenter GPUs.

V1 (2022-10-01) Model

This model was finetuned for ~500,000 steps at multiple different batch sizes and learning rates. It performs better than the current V2 model due to its longer training time, but I expect it to be surpassed soon.

The training captions used comma separated tags.

fluttershy, blush, pony, pomf, cute, adorable, daww, solo, scenery, scr800, flying, pegasus

Training Code

These models were trained using github:LunNova/translunar-diffusion.

Please see the stable diffusion training notes for more details.

Model Licenses

These releases are all licensed under the CreativeML Open RAIL-M License, as required for derivatives of the original stable diffusion model.

Cite as BibTeX 
@misc{pony-diffusion-model,
    author = {Luna Nova},
    title = {Lun's Pony Diffusion Models},
    year = {2022},
    url = {https://lunnova.dev/articles/pony-diffusion-model/},
    howpublished = {https://lunnova.dev/articles/pony-diffusion-model/},
    urldate = {2022-10-11},
    note = {lunnova.dev - Stable Diffusion finetuned on derpibooru}
}
« Quieting ROG Strix Helios top mounted case fans amdgpu gpu_recovery is impressive but required too often »
tagged machine learning image generation stable diffusion my little pony