--- widget: - output: url: "https://cdn-avatars.huggingface.co/v1/production/uploads/674edfd2e9adf4bc11f16a88/lXGd6iq19bdO0qc2qLYF6.png" license: unknown pipeline_tag: text-to-image base_model: - Laxhar/noobai-XL-Vpred-1.0 --- # ⭐3wolfMondAI-SDG⭐ An improved version of realMondAI-SDG to provide better realism and bring back toony styles support. ## 🟨Model Description lightblue - Developed by: Big Lasagna - Funded by: /sdg/ - Direct Download link - Also available on civitai.com - Also available on tensor.art - Artist tag gallery: rentry.org ### 🟨Uses lightblue This merge combines the best of StableMondAI-SDG and RealMondAI-SDG into one model. Its base style is a stable semi-realistic look while the realism tags turn on the realistic generations from RealMondAI, and using artist tags and style tags bring back the toony styles. Some can even be combined but some toony styles are trained so strong that they overwrite the realism completely. Play around with different weights to find a middle ground. 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 below for examples and comparison grids. ### 🟨Prompt Recommendations lightblue 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, newest, ``` Starter Negative prompt: ``` worst quality, ``` lightgray To increase the realism, add these tags to the positive prompt ``` (photorealism, realistic,) detailed background, ``` and these to the negative prompt ``` blurry background, blurry foreground, simple background, ``` lightgray If you want increased fur detail, try adding some of these tags into the prompt: ``` (detailed fur:1.2), fluffy, shaggy fur, ``` lightgray The realism combined with some tags will try to pull your generations toward human features, if this happens you can add "human (feature)" to the neg prompt, e.g. ``` human hands, human lips, ``` ### 🟨Generation Recommendations lightblue The following settings are recommended starting points: * Sampler: Euler A * Scheduler: SGM Uniform * Steps: 30 * CFG: 5.5 RescaleCFG of 0.6 is recommended. Euler A & DPM++ 2s ancestral as well as normal Euler and DPM++2M seem to work best, SDE samplers tend to generate more artifacts on some schedulers. Karras is not recommended. ## 🟨More Information ### 🟨Quantized version A kind anon created quantized versions of this model which you can use if you are very low on VRAM or for special setups like Mixmod. You can find them in the quantized model subfolder of the download section. ### 🟨Sampler / Scheduler Comparison Grid - base style lightblue CFG 5.0 / RescaleCFG 0.7 ### 🟨Sampler / Scheduler Comparison Grid - realism, photorealism lightblue CFG 5.0 / RescaleCFG 0.7 ### 🟨Style Examples Grid lightblue ### 🟨Artist Tag Examples - base style lightblue Also check this rentry with ~2000 artist tag example generations ### 🟨Artist Tag Examples - realism, photorealism ### 🟨RescaleCFG comparison lightblue ### 🟨Example Generations (including metadata) lightblue
Euler A / SGM UniformEuler A / NormalDPM++ 3M SDE / Align your stepsDPM++ 2M SDE / SGM Uniform
DPM++ 3M SDE / Align Your Steps 32DPM++ 3M SDE / Align Your Steps 32DPM++ 2S a / NormalEuler A / Uniform
### 🟨Uncommon Samplers Grid lightblue CFG 5.0 / RescaleCFG 0.7