REED FURRY MiX SDXL                  

Lora compatible with NAi/IL/Pony model training.

If you encounter any problems, please message me privately, I am happy to help anyone.

REED_FYRRY_MiX_SDXL is my first attempt at training a Furry male character model using the NoobAI system. The overall style leans towards anime, but it also carries a certain level of realism in fur texture and body structure.

When I first used it, I felt that the images were very clean, with stable character proportions. The head-to-body ratio, limbs, and facial structure all look natural. The eyes are expressive with a calm yet powerful vibe, and the transition between fur and ears is smooth, making the character look both attractive and believable.

My personal recommendations:

• Sampler: euler a or euler

• CFG: 3~6 is ideal; for short prompts, it can go as low as 2, while longer prompts should not exceed 7

• Resolution: 720p or higher with hires fix enabled; upscale to 1080p+ using Remacri for the best results

Additionally, I highly recommend pairing it with this upscaler model 👉 Remacri

✅ Positive Prompt

masterpiece,best quality,high quality,good quality,detailed eyes,highres,absurdres,incredibly absurdres,

🚫 Negative Prompt

worst quality,bad_quality,normal quality,lowres,anatomical nonsense,bad anatomy,anatomical nonsense,interlocked fingers,extra fingers,watermark,simple background,transparent,bad_feet,bad_hands,logo,text,bad_anatomy,signature,face backlighting,(worst quality, bad quality:1.2),jpeg artifacts,censored,extra digit,ugly,deformed anatomy,bad proportions,

Using it will significantly enhance fur texture, skin details, and eye clarity, giving your final images a clean and polished look.

FreeU can improve image softness, Eyeful enhances facial focus, and adetailer works great for fixing hands and feet.

Note that in complex poses or extreme angles, fingers and toes may sometimes appear distorted. Adding prompts like “perfect hands, perfect feet” can help fix this. The default backgrounds are usually simple, so if you want full scenes, it’s best to include detailed environment descriptions in your prompts.

If your goal is simply to create a good-looking and stable character, using the recommended settings above will give you solid results. However, if you want to explore different styles and expressions, feel free to experiment with other CFG values, samplers, and upscalers – this model is stable enough to handle various creative tests.

Thank you for your support. I’d love to see your creations with this model, so please consider sharing them in the Gallery. Your works are always inspiring to me.

The IL and Pony models will undergo asymmetrical updates with NAi in the future. Below is a brief note on the recently released versions.

v1.5 NAi: The recent major version update mainly focuses on optimizing image stability and embedding the related slots for the IL model.

v1.8 NAi: A comprehensive upgrade to the care system, enhancing compatibility with Lora for IL model training, and strengthening the personalization of model creators. It can be considered a major update.