World Furry Fusion – v1.0 (Refined)

📝Description

Checkpoint was created to generate images closer to the Loras (mainly Style Loras) using more precise prompts, resulting in images with more vivid colors and fewer problems, especially regarding the body structure of characters. The blending process uses the following base models:

• Illustrious XL - v2.0-stable

• NoobAI-XL (NAI-XL) - Epsilon-pred1.0-Version

The intention of the merge is to further approximate Lora's styles without losing its essence, such as "sketch images," "flat colors," "monochrome and grayscale," etc. The main highlight is the Illustrious version 2.0, which better captures the small details of the characters, in conjunction with a large part of NoobAI version 1.0, which includes a large database of trained images from the E621.

⚙️Recommendations

For more technical details about these versions, I recommend reading the articles at the link below:

Illustrious

https://www.illustrious-xl.ai/blog/7

https://civarchive.com/models/1489531?modelVersionId=1684946

NoobAI

https://huggingface.co/Laxhar/noobai-XL-1.0

https://civarchive.com/models/833294?modelVersionId=1022833

The model already includes VAE

• Sampler - Euler A or DPM ++ 2M Karras (Use as you prefer)

• Scheduler - Normal (ComfyUI / A1111 / Forge)

• Steps - 30 steps

• CFG Scale - 4 ~ 7

• Hires. Fix / Adetailer / FaceFix (Recommended for best results)

• Upscaler (Recommended for best results)

CFG Scale / Sampler Comparison Grid

To better view the image (which is at a resolution of 5284 x 4857 px), open it in a new tab

Prompt: masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by babanasaur, furry, furry female, anthro, animal ears, animal nose, snout, wolf, grey fur, body fur, grey eyes, 1girl, solo, breasts, looking at viewer, smile, teeth, dress, portrait, upper body, outdoors, forest, day, trees, plants, horizon, blue sky, clouds

CFG Scale / Lora Comparison Grid

To better view the image (which is at a resolution of 5284 x 4857 px), open it in a new tab

Prompt: masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by babanasaur, furry, furry female, anthro, animal ears, animal nose, snout, domestic dog, canine, yellow fur, body fur, blue eyes, short hair, 1girl, solo, breasts, looking at viewer, smile, teeth, sports bra, crop top, stomach, stomach, navel, collarbone, portrait, upper body, pov, simple background, white background

If you are generating images in Civitai, I recommend reading this article on how to use Civitai FaceFix.

How to fix faces in Civitai?

Positive prompt

masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, volumetric lighting,

negative prompt

worst quality, bad quality, low quality, lowres, signature, username, logo, jpeg artifacts, signature, watermark, artist name

The settings may change depending on the use of Loras, configurations, or where Checkpoint is running (Civitai or Local Generation), but all images in the Checkpoint gallery were created based on Civitai settings.

🤝Credits

We cannot forget this great creator of model.

• ONOMAAI

• L_A_X

• Fetch267

World Furry Fusion – v1.0 (Realism)

📝Description

Checkpoint created for generating realistic images (mainly furry characters) through more accurate and descriptive prompts using the NoobAI-XL base model, which, despite being a model entirely focused on anime, has ample flexibility to create any type of image. The checkpoint combines the following models:

• 3WolfMondAI-LastSDG

• World Furry Fusion

The intention is to merge and create a set of "realistic" images based on furry characters, but it's not limited to that; you can produce images with human characters, humanoids, feral animals, cartoons, and much more. This model is in V-PREDICTION mode.

⚙️Recommendations

Although the model is based on NoobAI - XL, we must pay attention to some practices that may change depending on usage (if the person is used to Illustrious, for example). Remember that NoobAI has some differences from Illustrious, so some settings may not work 100% most of the time. For this, access the official guide for the NoobAI - XL base model through this link:

Article in English

https://civarchive.com/articles/8962

Article is in Chinese (more complete, if you have any doubts, use a text translation program).

https://my.feishu.cn/wiki/S8Z4wy7fSiePNRksiBXcyrUenOh

Another key recommendation I'll leave here concerns the recommendations of the 3WolfMondAI-LastSDG model (which has most of this combination).

https://huggingface.co/Xeno443/3WolfMondAI-LastSDG#%E2%AD%90prompt-recommendations

• Sampler - Euler A or DPM ++ 2M Karras (Use as you prefer)

• Scheduler - SGM Uniform (ComfyUI / A1111 / Forge)

• Steps - 30 steps

• CFG Scale - 5 ~ 7

• Hires. Fix / Adetailer / FaceFix (Recommended for best results)

• Upscaler (Recommended for best results)

• RescaleCFG - 0.5 (RescaleCFG of 0.5 is recommended, but depending on desired style you can also disable RescaleCFG)

A lot of danbooru and e621 tags come with a strong bias towards a more anime/anthro look of characters, even generic tags like "female" or "furry". To generate more realistic characters you should leave these and just prompt for a species and add some features that belong to one of the genders, usually the model will then generate the desired result. Depending on species there might still be a tendency towards a more standard furry look.

If you want increased fur detail, try adding some of these tags into the prompt:

(detailed fur:1.2), fluffy, shaggy fur,

If it still tries to pull your generations toward human features, if this happens you can add "(feature) human" to the neg prompt, e.g.

human hands, human lips,

Sampler / Scheduler Comparison Grid

If you are generating images in Civitai, I recommend reading this article on how to use Civitai FaceFix.

How to fix faces in Civitai?

Positive prompt

masterpiece, best quality, newest, absurdres, highres, detailed background, realistic, photorealistic

negative prompt

worst quality, bad quality, low quality, lowres, signature, username, logo, jpeg artifacts, signature, watermark, artist name

The settings may change depending on the use of Loras, configurations, or where Checkpoint is running (Civitai or Local Generation), but all images in the Checkpoint gallery were created based on Civitai settings.

🤝Credits

We cannot forget this great creator of model.

• Odano441

World Furry Fusion – v1.0 (Standard)

📝Description

Checkpoint is my first and newest creation to generate new results (mainly furry characters) through more responsive prompts, and it has yielded quite satisfactory results. Checkpoint currently combines two of the main models currently used in Civitai:

• Wai Illustrious

• Nova Furry XL

The intention is to combine, through fusion, a set of images geared towards the "anime" style with a good dose of "furry". Therefore, don't limit yourself to just that; you can produce SFW and NSFW content, as well as humanoid characters, humans, famous cartoon characters, and more, whatever your imagination allows.

During post-training (merge), I noticed that there were a few artifacts during the generation of some images (this bothered me a lot), so I decided to add a VAE to add more colors and remove any artifacts from the images. I chose this VAE (Illustrious-XL-v2.0) because I am more familiar with it. If you have any questions about what a VAE is, I suggest reading this article:

https://stable-diffusion-art.com/how-to-use-vae/

⚙️Recommendations

• Sampler - Euler a or DPM ++ 2M Karras (Use as you prefer)

• Steps - 30 steps

• CFG Scale - 4 ~ 7

• Hires. Fix / Adetailer / FaceFix (Recommended for best results)

• Upscaler (Recommended for best results)

If you are generating images in Civitai, I recommend reading this article on how to use Civitai FaceFix.

How to fix faces in Civitai?

Positive prompt

masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, 

negative prompt

bad quality, worst quality, worst detail, sketch, lowres, jpeg artifacts, signature, watermark, username, artist name

The settings may change depending on the use of Loras, configurations, or where Checkpoint is running (Civitai or Local Generation), but all images in the Checkpoint gallery were created based on Civitai settings.

⚠️Note

I'm open to feedback on the model and plan to add new versions with different styles in the future, including my Loras created so far (I need to study this part a bit more to create a very flexible model with a unique and specific style).

🤝Credits

We cannot forget these two great creators of models.

• WAI0731

• Crody

• Fetch267