<h3 id="krea2-v1:"><strong>krea2-v1:</strong></h3><p>I suggest using an fp8 or bf16 model as the base model. Due to my local memory limitations, I used an int4 model to demonstrate the output effect. However, LoRa was trained on the original raw model, so I suggest using it on a higher precision model. Please show your images and provide relevant suggestions on the model.</p><h3 id="anima:"><strong>ANIMA:</strong></h3><p>v2 has updated the training set, added some recent new characters and skins, and added some maps with richer environments. I trained this version three times. The art style of the first two times was always unsatisfactory, so the number of training steps has been increased a lot this time. If you feel that the fingers occasionally break, you can appropriately reduce the model strength.</p><h3 id="illustrious:">Illustrious:</h3><p>v2 Notes: Since the training set of version v1 mainly consisted of character illustrations, the composition diversity was relatively limited. Version v2 enriches the training set.</p><p>Version 2 is recommended to have a weight of 0.8</p><p>This is the art style of the game Brown Dust 2.</p><p>Recommended weight 0.6-0.8.</p><p></p><h3 id="if-you-like-my-model-please-like-and-share-some-pictures-this-is-my-motivation-to-keep-updating.thank-you-for-your-support."><strong>If you like my model, please like and share some pictures; this is my motivation to keep updating.Thank you for your support.</strong></h3><p></p>

CC—BrownDust2 style

BD2V3-000037.safetensors

Files with SHA256: 1e1c4c696b3cc8eb6dbe87c330c5f2ee3d2ffd0a611904fadf2cdcd9e359111f