⚡ 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 ZIT 2.0 (Kofi)
Event Horizon XL 7.0 (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 versions 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.
⚙️ Normal SDXL Recommended Settings:
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
Description
It's the first Illustrious version. It's obviously more focused in illustrations and cartoons and while it's less photorealistic than its counterpart, EHxl 5.0, it produces very interesting aesthetics with a lot of drama or extra flavour. See the gallery. All in all, I think It's a very interesting alternative to the XL version. The more choices the better.
Let me know about your feedback in the comments.
FAQ
Comments (5)
Illustrious v1 has one of the worst promp adherence i ve ever seen in any realistic checkpoint. It seems to know almost nothing regarding danbooru tags and ILXL prompt sequences. And if this wasn't enough, most LoRA won't work at all. For me this is a hard pass on Illustrious v1.
In all honesty, the illustrious version it's the one I tested the less. In this case, I used Illustrious to enhance anatomy, that was the only goal (danbooru tags are expected not to work in hybrid checkpoints like this one). And yeah it sort of worked on that regard but probably prompt adherence was affected at the same time (i had the same problem with the illustrious version of nexus). Being said that, Both v5.0 and v6.0 have no problems at all with prompt adherence (much better than 4.0 and 4.5) and in 6.0 i even managed to improve anatomy significantly without resorting to Illustrious. It's free to use on TA (no yellow buzz needed) so you can test that one if you want. In any case, hybrid checkpoints (illustrious-sdxl) are indeed tricky to work with.
On the other hand, I have pure illustrious checkpoints like Anime, Cartoon and EHIllustrious that will work with Danbooru tags. So maybe you want to check those out intead.
Thanks for the feedback, much appreciated.
@ElectricDreams That makes sense. Tho, using natural‑language prompting on any ILXL checkpoint is basically like flipping a coin and hoping it lands on the side you picked: not accurate or reliable at all. I was looking for a good realistic checkpoint WITH solid prompt adherence AND strong danbooru tags knowledge. This kind of checkpoint is indeed very rare, but I can name two that meet these criteria for the most part. Yet they aren't perfect and they both still struggle with facial expression diversity and and require a low CFG score of about 3, which supposedly doesn't help with prompt adherence (and yet they succeed at it), to achieve very high realism (not magazine cover photos, i'm talking actual IRL realism): Illustrious Realism by llikswonskcalb and Real Hallucinations by ViciousTulpa. Illustrious Realism is the best at realism without specific tags or LoRA by a significant margin, tho.
What is difference between these models: Event Horizon Xl Illustrious v1.0 vs Event Horizon Illustrious v4.0 ???
BTW it gest confusing when you put Illusttrious into EHXL model group, should it be added into EHI model group?
EventHorizonillustrious is obviously anime oriented. Event Horizon XL Illustrious 1.0 (that you can find here) was an experiment / adaptation of the normal EH series but using Ilustrious to improve the anatomy while remaining photorealistic. Fortunately in EH 6.0 the anatomy was improved without resorting to Illustrious or a hybrid checkpoint so i don't think we're gonna see more Ilustrous versions here in a short term.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.