⭐RealMondAI-SDG⭐
A model to bring better realism capabilites to StableMondAI-SDG
- Prompt recommendations
- Generation recommendations
- Sampler/Scheduler comparison
- Style examples
- Artist examples
- RescaleCFG comparison
- Example Generations
🟨Model Description
- Developed by: Big Lasagna
- Funded by: /sdg/
- Also available on civitai
🟨Uses
This model adds realism capabilities to stableMondAI-SDG. The base style supports strong realism, artist tags are still supported but some may overcome
the realism and turn it back into toony style. It is recommended to use this model for realistic gens and StableMondAI for toony styles.
This model is in V-PREDICTION mode.
Prompts need to use danbooru/e621 tags, no Natural Language Support is added at this point. Use noobAI quality tags at your own discretion.
See example pictures below for style tag examples.
🟨Prompt Recommendations
Start with a basic prompt and work from there. All IllustriousXL/noobAIXL quality tags are recognized but these models work better with leaner prompts.
Starter Positive prompt:
masterpiece, best quality, (realistic, photorealistic)
Starter Negative prompt:
worst quality, blurry background, blurry foreground,
🟨Generation Recommendations
The following settings are recommended starting points:
- Sampler: Euler A
- Scheduler: SGM Uniform
- Steps: 28-32
- CFG: 5
RescaleCFG of 0.7 is recommended, but depending on desired style it also works well without it.
Euler A & DPM++ 2s ancestral as well as normal Euler and DPM++2M seem to work best, the SDE samplers tend to generate more artifacts on most schedulers. Karras is not recommneded.
🟨More Information
🟨Sampler / Scheduler Comparison Grid
CFG 5 / RescaleCFG 0.7
🟨Style Examples Grid
🟨Artist Tag Examples
🟨RescaleCFG comparison
🟨Example Generations (including metadata)
| Euler A / SGM Uniform | Euler A / SGM Uniform | Euler A / SGM Uniform | Euler A / SGM Uniform |
|
|
|
|
| Euler / Beta | DPM++ 2M SDE / Automatic | DPM++ 3M SDE / Normal | DDIM / Automatic |
|
|
|
|
🟨Uncommon Samplers Grid
Model tree for Xeno443/realMondAI-SDG
Base model
Laxhar/noobai-XL-1.0
Finetuned
Laxhar/noobai-XL-Vpred-0.5
Finetuned
Laxhar/noobai-XL-Vpred-0.6
Finetuned
Laxhar/noobai-XL-Vpred-0.65
Finetuned
Laxhar/noobai-XL-Vpred-0.75
Finetuned
Laxhar/noobai-XL-Vpred-1.0








