<h1 id="overview">Overview</h1>Basically a silly hyper version of my <a target="_blank" rel="ugc" href="https://civarchive.com/models/2311601/macromastia-naked-krea-2-ideogram-4-flux-z-image-etc">Macromastia (Clothed) LoRA</a>.The model is pretty straight forward. Use the trigger early in your prompt. Further descriptions to the breasts position, framing and focus can help a lot to emphasize the effect.Sometimes it creates thicker or chubby bodies, for that you can include descriptors like <code>slim</code> or <code>skinny</code> or use negative prompts.Values over <code>1.0</code> may produce heavy artifacts. Decrease strength if you encounter artifacts. Most samples use a strength of <code>0.9</code>. Breast size sliders work, but use at own risk.Use lower strengths when only boosting the size for other LoRAs, like <a target="_blank" rel="ugc" href="https://civarchive.com/models/2688234/realism-engine-ideogram-4-krea-2">Realism Engine</a>.For more, have a look at the example images/videos.<h2 id="krea-2-turbo-v1">Krea 2 Turbo - V1</h2>Use the trigger <code>gtsmst</code> and describe the breast/cleavage in some detail. Use the WAN 2.1 VAE for more realistic outcomes. Use the <a target="_blank" rel="ugc" href="https://civarchive.com/models/2728234/krea2filterbypass?modelVersionId=3067151">filter bypass</a> LoRA for better results.<ul><li>Training model: <a target="_blank" rel="ugc" href="https://huggingface.co/krea/Krea-2-Turbo">Krea 2 Turbo</a> + <a target="_blank" rel="ugc" href="https://huggingface.co/ostris/krea2_turbo_training_adapter">Training Adapter</a></li><li>LoRA strength: 0.5-1.0</li><li>Sampler: euler / euler a / euler+beta57</li><li>Steps: 8+</li><li>VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/vae">WAN 2.1</a></li></ul><pre><code>gtsmts, A slim, fit woman with colossal breasts is taking a mirror selfie, from a slight angle. She's standing in a dressing room, some clothes lying on the floor and bench behind her.</code></pre>

Files with SHA256: 284168ef0c0577d47a890916730756ab3ddfcabe9dcbd9e691584822f02ed907