Updated: Aug 17, 2026
base modelDownload
2 variants available
fp8 SafeTensor
krea2EHNexus_v1.safetensors
8-bit, smaller file • 17.95 GB
Verified: 8 days ago
SafeTensor
EHNexus Krea is a high-capacity Krea-based checkpoint focused on strong realism, flexible prompting and a wider expressive range than standard general-purpose models.
This release uses a mixed-precision architecture combining FP8 and FP16 weights. Because of this, the checkpoint is considerably larger than a typical FP8 release, coming in at around 18 GB. This is intentional and worth keeping in mind before downloading: it is not a fully FP8-compressed model.
EHNexus Krea is designed for:
Photorealistic and cinematic imagery
Natural skin, faces and body detail
Strong prompt adherence
Fashion, portrait and editorial photography
Darker, more mature visual themes
Broad creative freedom with fewer aesthetic constraints
Detailed environments and complex compositions
The model is particularly suited to users looking for a less restricted, more versatile Krea experience, while retaining the strong photographic qualities of the base architecture.
Show more


2.3K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
8.1K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

License:
Get the full checkpoint at the best price from the official Ko-fi store.
Want to try it first? Generate up to 85 free images per day at the highest quality with Event Horizon here.
Join the Electric Dreams Discord for support, free tools, and everything related to AI image generation.
→ Get it now at a lower price.
🛒 Ko-fi
✅ Card & PayPal accepted
✅ No crypto, no Buzz, no queues
✅ Instant download
✅ Priority support
Also available:
Krea2EHNexus v1.0 (Kofi)
Event Horizon Nexus XL Aenima v3.0 (Kofi)
Event Horizon Nexus XL Aenima v2.0 (Kofi)
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
Join the Electric Dreams Lab Discord to meet fellow AI creators, share ideas, and discover what's coming next.
Click here to join the Discord!
IMPORTANT: ZIT models are currently not available on Civitai's generator. You can try them for free on TensorArt.
Event Horizon ZIT
https://tensor.art/models/975520856052632797/Event-Horizon-ZIT2
Event Horizon Nexus ZIT
https://tensor.art/models/984780105463163349
⚙️ 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: 1240x1660 / 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.



