UPDATE V3: New dataset. Includes a variety of different subjects and landscapes (V1 &amp; V2 only had women in the dataset). Better prompt adherence, better body anatomy. Includes different lighting.<hr />This uses my trained Zi lora/checkpoints from Illustrious mixed in with Anima Base!Works very well with natural language.<hr />YOU NEED:qwen base encoder &amp; qwen image vae<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f500813c-c5e6-44fd-ad51-59172918422b/original=true/f500813c-c5e6-44fd-ad51-59172918422b.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/631407cf-578d-43f9-b527-c3004b61489f/original=true/631407cf-578d-43f9-b527-c3004b61489f.jpeg" />All gallery images should have metadata so you can drag and drop to see the exact things you need.<hr />SETUP:Steps: 30 - 50CGF: 4 - 5Sampler: Eular/Eular A/res 2s (haven't tested others)

Zi-Anima

Small update. Lowered the file size removing the VAE and CLIP inside the checkpoint. Changed from Preview 3 to Base Anima.

Files with SHA256: 01c8fcc0befdeea51c8ea0672668535cd375560b27ba2c2f28a8ed4c7d3a5634