Model Information


Description
Note: This model has an embedded VAE, not sure if it was removed on upload or not.
PonyRAP is a flexible Pony model merge made from merging multiple Pony model test merges. Primarily aimed at realistic images, it can do fantasy and semi-anime style when prompted. PonyRAP also does a good job of reproducing character LoRAs and can produce semi-realistic images without a negative or extra positive tokens.
Main Showcase uses Hires. Fix
Second post will be without Hires. Fix
Recommended Settings:
Steps: 30
CFG scale: 6
Sampler: Euler a
Hires. fix
Upscaler: 4x_NMKD-Siax_200k or 4x-UltraSharp
Steps: 20
Denoise strength: 0.25-30
Positive Prompt
score_9, score_8_up, score_7_up, photo of {prompt}, photo background, source_photo, ultra-detailed, (analog film grain), high quality, Fujifilm XT3Negative Prompt
score_6, score_5, score_4, (lowres, blurry, blur, illustration,3d, 2d, painting, sketch, cartoon, anime, airbrushed, grainy, watermark:0.95)PonyRAP
PonyRAP v1.0
183downloads
Download ModelModel Details
- Type
- AI Model
- Task
- text-to-image
- Subtype
- Safetensors / Checkpoint AI Model
- Created
- Updated
- June 7, 2026