Stable Diffusion
V4
model_id: v4
<p>Please experiment with the weight on this Lora. </p><p>0.8 gives a Zankuro experience but less weight like 0.5 or 0.6 produces nice anime styles and colors without the extreme Zankuro style.</p><p>Update v4 (02/17/2024) - New version is more style accurate and has more interesting poses.</p><p>🔞 Warning! 🔞 This Lora is very naughty because it matches Zankuro's style. Please use this Lora with caution.</p><p>Please experiment with the weight. Some images look nice with 1.0 weight while others look better with 0.7 weight.</p><p>V4 Details</p><p>Trained on: 881 images</p><p>Training Model: AnyLoRA_noVae_fp16-pruned</p><p>flip_aug: False</p><p>Num of Repeats: 1</p><p>Unit is Epochs or Steps: Epochs</p><p>Number of Epochs or Steps: 10</p><p>Training Batch Size: 4</p><p>Total Steps: 2202</p><p>Resolution: 512</p><p>Network Dim: Dim 32 and Alpha 16</p><p>Lora Creation Process took: 00:43:21</p>
NSFW samples are gated
This model produces NSFW content. Log in and enable NSFW in your account settings to view samples and run the model. The API and model parameters below are accessible regardless.
Use V4 via the ModelsLab API
Send a POST request to the relevant endpoint with your API key and model_id="v4". The API does not enforce the same NSFW gating as the web playground — content moderation is handled by your account-level policy. Sign up to get an API key.