These are some of my tests for Make Art Not Goon aka Animagine XL Realistic.

To help, say:

Yes - in a measurable sense, e.g. "3 in 5 of my gens are better".
No - please help with a "specific prompt" which needs improvement:

1. prompt following, character accuracy

2. anatomy, hands, poses, positions

3. interesting composition, seed variety, bias (gender, ethnicity, etc)

4. lighting, color, special effects, realism

5. faces, emotions, expressions

I make the merges with ComfyUI, I test new block merge permutations using a high resolution, 20-25 steps, cfg 1.2 + 0.8 perturbed attention guidance to make a 'total cfg' in the 2-3 range, then save new permutations that seem better for that prompt. After a few weeks, thousands of permutations, I've usually got a new version. I test prompts with and without realistic/photorealistic, a few art styles, with and without masterpiece, absurdres.

I keep the clip_l, clip_g and vae identical to the original Animagine XL 4.0. I try to keep as much weight from the original unet, in particular that which controls composition, prompt following and lighting.

License

This model adopts the original CreativeML Open RAIL++-M License from Stability AI without any modifications or additional restrictions. The license terms remain exactly as specified in the original SDXL license, which includes:

• ✅ Permitted: Commercial use, modifications, distributions, private use

• ❌ Prohibited: Illegal activities, harmful content generation, discrimination, exploitation

• ⚠️ Requirements: Include license copy, state changes, preserve notices

• 📝 Warranty: Provided "AS IS" without warranties

Please refer to the original SDXL license for the complete and authoritative terms and conditions.