This is a lora that focuses on bottomheavy body shapes. It is trained on 100% anime/furry data, but can be made to produce realistic images just fine. You can adjust the body size with lora strength as needed (it should handle smaller sizes as well). See Training Data for tags list<h3 id="changelog-2026-01:"> Changelog 2026-01:</h3><ul><li>Just decided to revive an old lora as a test for Flux2 Klein-4b-base. I'm starting to prefer Klein over Z-image, but ill wait and see what gets better adoption.</li></ul>

hyper bottom heavy

I cleaned up the dataset a little, but its pretty much the same as v1 as far as tags go. Just wanted to revive this old lora on a modern model to see how it performs.Training Details:<ul><li>I used Diffusion Pipe for this training, anything not listed below, was default value.</li><li>resolutions = [[768, 512]]</li><li>enable_ar_bucket = true</li><li>micro_batch_size_per_gpu = 2</li><li>gradient_accumulation_steps = 8</li><li>type = 'lora'</li><li>rank = 32</li><li>dropout = 0.1</li><li>type = 'AdamW8bitKahan'</li><li>lr = 1e-4 (probably could have been higher)</li></ul>

Files with SHA256: 1a7164eaf22507ffc639dc28df7169d25446069e17e56cf3a41d7df30ad637d2