Model Information


Description
A checkpoint that by default produces a semi-realistic picture, example prompts are in the checkpoint images.
Positive Prompt (optional and generally not required):
masterpiece, amazing quality, best quality, ultra-detailedNegative Prompt (mostly important):
lowres, bad quality, worst quality, bad anatomy, jpeg artifacts, ugly, poorly drawn, blurry, censored, artist name, signature, watermarkIn some cases, you can add to a negative prompt:
wet, wet skin, blushRecommended settings:
Steps: 25-35
CFG scale: 4-7
Sampler: Euler a / DPM++ 2M
Scheduler: Karras
Model Recommended Resolution: 768x1344, 832x1216, 768x1280, 704x1408, 1024x1536
Version V1 based on Strange Thing Mix Real V1 and Strange Thing Mix Anime V1
Strangeformula
198downloads
Download ModelModel Details
- Type
- AI Model
- Task
- text-to-image
- Subtype
- Safetensors / Checkpoint AI Model
- Created
- Updated
- May 24, 2026