just1n (Pony V3) is a character LoRA trained on Pony Diffusion XL (SDXL 1.0) for the trigger word just1n. It was built from 264 captioned reference images using Civitai’s Spine Controller and ai-toolkit, with a 32-rank LoRA at 1024px resolution, cosine learning-rate schedule, Adafactor optimizer, and joint UNet + text-encoder training. The run targeted a consistent male character read — mature, bara-leaning, realistic proportions, East Asian features, and recurring tags like short dark hair, glasses, facial hair, and an everyday “married father” look in casual settings.
Fifteen epoch checkpoints are available from this training job (the full 20-epoch run did not complete). Sample generations skew toward upper-body and full-body portraits with natural lighting, outdoor or indoor photo backgrounds, and a range of body types from plump to muscular. Use just1n in your prompt at modest strength (roughly 0.7–1.0 to start) alongside quality tags; the bundled negative prompt from training (bad quality, low quality, jpeg artifacts, blurry, watermark, etc.) is a good baseline. Epoch 10–15 is usually a sensible starting range for Pony XL, but compare sample images across epochs to pick the best fit for your workflow.
Description
Recommended: Pony V3 — continued from epoch 15
Alternatives:
• Pony V3 (refined)
• Pony V3 — resume
Version notes (what goes in the notes field)
Trigger: just1n
Base: Pony Diffusion XL (SDXL 1.0)
Clip skip: 1
Strength: start at 0.7–1.0
Continuation training from Pony V3 epoch 15 (original run stopped at 15/20 epochs).
Same 264-image dataset; 15 additional epochs at 1024px, rank 32/alpha 32, Adafactor, cosine LR, UNet + text encoder.
Recommended starting point: epoch 12–15 (compare bundled samples).
Not interchangeable with Ernie or Illustrious versions on this model page.
Paragraph 1 — what it is
│ just1n (Pony V3 — continued) is a character LoRA for Pony Diffusion XL, trained on the trigger word just1n. It continues from the epoch-15 │ checkpoint of the original Pony V3 run (which stopped early at 15 of 20 planned epochs), using the same 264 captioned reference images. Training │ used Civitai’s ai-toolkit at 1024px, rank 32 / alpha 32, Adafactor, cosine learning-rate schedule, and joint UNet + text-encoder training.
Paragraph 2 — how to use it
│ The character read is consistent with the other redo-just1n versions: mature, bara-leaning, realistic male proportions, East Asian features, short │ dark hair, glasses, facial hair, and an everyday “married father” look in casual or outdoor settings. Use just1n at modest strength (about 0.7–1.0 │ to start). Compare sample images across epochs 12–15 before picking a publish checkpoint — later epochs are usually stronger, but not always. This │ version is Pony-only; use the Ernie or Illustrious versions on this page for those bases.
Tags
character, lora, pony, sdxl, realistic, bara, male, east asian, glasses, facial hair, mature, just1n