blinkdotleh/Grim Noire vPred
Make sure to use UI that supports v-prediction , otherwise you will get a noisy blob! Main parameters: Steps: 28 CFG: 3-5 Sampler-scheduler: euler/euler a-normal, DDPM-exponential (better noses) CFGZeroStar and sometimes Self-Attention Guidance: default for difficult backgrounds Try to BREAK prompts into parts by 75 tokens max, this goes for most models.. Positive prompt: number of characters (1girl/1boy), character name, artist prompt, scene/environment/camera angle, action, expression, items, quality prompts (masterpiece, best quality) some heavily stylized characters might require prompt: n
| Author / organization | blinkdotleh |
|---|---|
| Downloads | 2.7K (as reported by Civitai) |
| Likes | 148 |
| Task | text-to-image |
| Created | 9 February 2026 |
| Last updated at source | — |
Popularity, last 3 days
2,659 now (+26 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from blinkdotleh
- blinkdotleh/Ultra photo-realistic workflow | refiner, upscaling, FaceDetailer (+index elements), inpainting, controlnet, Civitai MetModel
- blinkdotleh/MiniMax H3 with SEEDVR2 upscaler + Ollama prompt helper | 16GB VRAM 32GB RAMModel
- blinkdotleh/Grand Design ILXL2.0Model
- blinkdotleh/Blink's ANIMA (+2.9B) workflow - ti2i AIOModel
- blinkdotleh/AnyPastelKa AnimaModel
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 Information may be incomplete or out of date.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.