Generates ankle socks reliably. Current models apparently only generate calf-, knee- or even thigh-high socks when prompted with "ankle socks" or "ankle_socks."Trigger words are "ankle socks" or "ankle_socks." This version uses the same core dataset as v1.0, but with attention masking to improve the training process and subsequently, model flexibility. Model was trained in OneTrainer using the DADAPT-LION scheduler with a constant LR of 1.0 over a dataset of 168 images with a batch size of 12 and a gradient accumulation of 16 steps for a total of 290 epochs (4060 steps).LoRa weights were normalized at 1.0 (the recommended weight to use this model) using the invaluable Stable Diffusion ai-toolkit (<a target="_blank" rel="ugc" href="https://github.com/ostris/ai-toolkit">https://github.com/ostris/ai-toolkit</a>).Sample images include all metadata for recreation in your own environments; highres. fix and ADetailer (just to make faces pretty) were used to generate the samples. No other embeddings, LoRa or manual inpainting were used during/after generation.You're free to use this however you wish. It's socks. Would love to see some creations using this LoRa!

Ankle Socks LoRa

Same dataset, but with masking to focus attention. LoRa is much more consistent, promptable and flexible compared to v1.0.

Files with SHA256: aacebe24be28956bfa617603cfec87ec756ebcc9b49b25300aefd7b1f8dc0c6f