⚡ EARLY ACCESS — Limited time This model is available for direct download for 15 days only. After that: Generation Only on Civitai. No more downloads here.
→ Get it now for much cheaper prices, skip the wait:
🛒 Ko-fi · TensorArt ✅ Card & PayPal accepted — no crypto, no Buzz, no queues ✅ Instant download · Priority support
Also available:
Event Horizon Nexus XL Aenima v1.0 ( Kofi)
Event Horizon Nexus ZIT 2.0 (Kofi)
💎 Get the complete Event Horizon collection with all the future updates included→ Ko-fi
⚙️ Recommended settings with Z-Image Turbo versions:
8 steps, cfg1, Euler or DPM++ 2s a RF sampler, Normal or Simple or Beta scheduler, 832x1216, 1024x1536 or 1280x1920 pixels
Upscaling:
8 steps, cfg1, Euler sampler, Normal or Simple or Beta scheduler, 1.5x upscale
Important: remember that you need to place qwen3_4b.safetensors in the text_encoder sub folder and ae.safetensors in the VAE sub folder for Z-Image Turbo to work properly.
⚙️ Recommended settings with SDXL AENIMA version
Sampling method: DPM++ 2M SDE Karras
VAE: is already Baked In
Sampling steps: 30+ Steps
Resolution: 1344x1792 / 1408x1888 CFG: 3-5
Clip Skip: 2
Upscale: 1.5 upscale (0.3 - 0.35 denoise)
Upscalers: 4x_NickelbackFS_72000_G / 4x_foolhardy_Remacri / 4x_NMKD-Siax_200k
Dmd2 lora: (dmd2 lora is highly recomended with SDXL) LCM Karras scheduler, 14 steps, CFG:1)
⚙️ Recommended settings with SDXL version
Sampling method: DPM++ 2M SDE Karras
VAE: is already Baked In
Sampling steps: 30+ Steps
Resolution: 832x1216 / 896x1152 CFG: 3-5
Clip Skip: 2
Upscale: 1.5 upscale (0.3 - 0.35 denoise)
Upscalers: 4x_NickelbackFS_72000_G / 4x_foolhardy_Remacri / 4x_NMKD-Siax_200k
⚙️ Recommended settings with DMD2 lora:
Sampler: LCM Karras / Exponential
CFG: 1-1.3 (recommended is 1)
Steps: 8 - 12 steps
Resolution: 896x1152 / 832x1216
Clip Skip: 2
VAE is bundled in, you don't need to download anything else.
Description
Improved IQ over 3.0. Much better at details. Better skin detail and lighting. Better prompt adherence.
FAQ
Comments (2)
I'm coming from version IL1. The checkpoint creates very attractive faces. However, it hardly adheres to IL-typical tags such as “looking at another.” This is unfortunate, as that is precisely what defines IL. Would it be possible to integrate Danbooru tagging?
Yes. Illustrious was an experiment. Prompt adherence was not optimal in this case. I dropped illustrious for realistic checkpoints atm. I recommend using the latest versions of Nexus, anyways. Thanks for passing by.