homoludens/CinEro-NG-Krea2
ALWAYS LOOK INTO MY SAMPLES BEFORE DOWNLOADING TO UNDERSTAND IF THAT VERSION MEET YOUR EXPECTATIONS. Recommended generation parameters can be easily extracted in ComfyUI by dropping the sample into its window. This is the CinEro NG Krea 2 series of checkpoints. Aimed to deliver the dark cinematic SFW / NSFW picture with unrestricted Qwen 3 VL Heretic Text Encoder. Trained with sci-fi horror themed moody portraits dataset. Developed mostly to be used in ComfyUI, but should work in other Stable Diffusion generation software. v3e TL;DR; Main difference from v3-alpha is better ethnicity adherence
| Author / organization | homoludens |
|---|---|
| Downloads | 3.1K (as reported by Civitai) |
| Likes | 184 |
| Task | text-to-image |
| Created | 13 October 2026 |
| Last updated at source | — |
Popularity, last 3 days
3,063 now (+115 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from homoludens
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.