⚡ EARLY ACCESS — Limited time only. This model is available for direct download for 15 days only. After that: Generation Only on Civitai. No more downloads here. Get the best pricing in the official store.
→ 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
The most ambitious overhaul so far. Now with Better VAE with cleaner image.
More details. Better prompt adherence. True SOTA IQ.
Improved lighting.
Better Image composition.
Images are 80% better.
FAQ
Comments (5)
Hi! I've been trying to understand the best way to use SDXL as a refiner pass (for lighting + realistic materials) over base ILX or Pony renders. And your model looks amazing and lovely. Any thoughts on whether the workflow I have in mind will bear healthy fruit? :) Any insights would be amazing + thanks!
Yeah! it should work! go for it!
Again with the model cards...
I am filtering for Illustrious models and as usual a model says "Updated", but once I get to the model-card it says another model was updated.
Please, do not mix base-models in the same model card, it is becoming IMPOSSIBLE to search for models if every other model is going to say "Updated" when nothing has been updated for several months.
As something something Civitai is now can you even imagine what it would look like if every singe creator had to make a "separate" page for each flavor of model base for each different style they did?
Apparently you cannot, it's human to be self serving and inward turned, but try for just a moment to put yourself in the shoes of not a leech, er, I mean not a "collector" of other's work, time, expense, but instead, spend a moment in their much much larger shoes.
@pursuit_of_beauty As I said, when I scroll the models page and see a model I recognize with the "Updated" tag, I expect the base model to be improved.
Many creators name their models like "Imaginary Checkpoint XL" or "Imaginary Checkpoint F1", this is the case with many models made by Copax, StableYogi, Hades, and other huge creators. Awesome creators btw, but when I scroll that discovery page and filter for SDXL/PDXL/ILXL models, I don't want to see that the last update to that model was 6 months ago and the card only got an update because the creator decided to upload a model I can't run.
It must be real dense in there if you can't see my point of view, but I suppose that's not a problem you have, probably because you either only generate online or because you have much more VRAM to play with. And, since we still have free speech in most of this world, I decided to give my two cents. Why you're getting hurt about it I don't know, not my problem. My problem is a clutter when searching for models, pretty simple actually.