Read the version details and recommendations in the "About this Version" section first.
LoRA, trained at Civitai based on furry artist Freckles
or known as soto
Support the artist using these links:
https://www.patreon.com/Freckles
https://www.furaffinity.net/user/soto
https://www.furaffinity.net/user/freckles
https://www.deviantart.com/freckleddoggie
https://www.weasyl.com/~Freckles
https://itaku.ee/profile/freckles
https://sotosrabbithole.tumblr.com
https://frecklednotepad.tumblr.com
https://bsky.app/profile/elfreckles.bsky.social
https://bsky.app/profile/freckles-art.bsky.social
https://www.picarto.tv/Freckles
1) Always use the tag by freckles
2) This LoRA was based on the Illustrious
3) Even though the Illustrious base model is used, some other models may have some inconsistencies in the images, especially in the eyes and hands, if used in Civitai, use some Embedding / Face Fix to get better results. For those who use Comfyui, the best results will be with some Hirefix / DDetailer to improve the image of the character's face.
4) LoRA weight change in Civitai is at your discretion
5) To better use Lora in Civitai, I recommend using VAE (SDXL VAE) to reduce errors in the details of the hands and eyes.
6) Check first for a model compatible with your chosen image, some models affect Lora in the final result of the image generation for some types such as: furry, human, realistic images, etc. Therefore, the same model may not always be suitable for different types of images.
7) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:
Illustrious (v1.0)
<lora:Freckles_Style_Lora_Illustrious:1>Note: the number at the end of the Lora name (1) refers to the Lora weight. In image generators, we have a weight slider, but if you want to "force" it, use the same number as the image generator slider in the positive prompt, for example:
Illustrious (v1.0)
Civitai slider = 1
positive prompt: <lora:Freckles_Style_Lora_Illustrious:1>8) I added tags related to the artist's best-known characters, if you want an image close to the character, don't forget to enter the character's name, I will leave examples of prompt positive right below each character:
Pecas
by freckles, pecas (freckles), furry, furry male, anthro, animal ears, animal nose, snout, domestic dog, canine, orange fur, white fur, body fur, two tone fur, white hair, white eyebrows, grey eyes, floppy ears, tail, tuft, 1boy, solo, completely nude, penis, testicles, flaccid, looking at viewer, :3, smile, hands on hips, cropped legs, white border, dark green background, simple background, gradient backgroundJuniper
by freckles, juniper (freckles), furry, furry female, intersex, gynomorph, anthro, animal ears, animal nose, snout, equine, horse, brown fur, white fur, body fur, two tone fur, white hair, long hair, huge ahoge, green eyes, huge breasts, nipples, sheath, fully sheathed, huge penis, huge testiles, muscular female, muscular intersex, ass, thick thighs, tail, 1girl, solo, completely nude, collarbone, stomach, smile, lips, looking at viewer, erection, veiny penis, standing, arm support, contrapposto, outside border, white border, dark yellow background, simple background, gradient backgroundCayenne
by freckles, cayenne (freckles), furry, furry male, anthro, animal ears, animal nose, snout, equine, horse, (red fur:1.4), body fur, brown hair, long hair, hair over eyes, big penis, big testicles, markings, gloves (marking), leg markings, socks (marking), muscular male, big muscles, large pectorals, dark nipples, thick thighs, tail, 1boy, solo, abs, navel, stomach, bulge, detailed bulge, topless male, underwear, underwear only, gold thighhighs, gold gloves, fingerless gloves, elbow gloves, spread legs, feet out of frame, sitting, from below, low-angle view, (bulge focus:1.4), white border, purple background, simple background, gradient backgroundAlmond
by freckles, almond (freckles), furry, furry female, anthro, animal ears, animal nose, snout, beef cattle, bovine, cattle, hereford cattle, orange fur, tan fur, body fur, two tone fur, blonde hair, short hair, hair over eye, one eye obstructed, orange eyes, horns, huge breasts, hyper breasts, nipples, plump labia, huge ass, wide hips, thick thighs, tail tuft, 1girl, solo, plump, navel, on glass, against glass, breasts on glass, breast press, completely nude, looking at viewer, cropped legs, upper body, white border, light blue background, simple background, gradient backgroundSoto
by freckles, soto (freckles), furry, furry male, anthro, animal ears, animal nose, snout, lagomorph, leporid, rabbit, brown fur, body fur, brown hair, ear piercing, ear ring, multicolored ears, yellow eyes, short hair, huge penis, huge testicles, markings, ear markings, gloves (marking), leg markings, socks (marking), toeless (marking), huge ass, thick thighs, tail, 1boy, solo, completely nude, hands on hips, standing, large penis, large testicles, erection, veiny penis, full body, feet, barefoot, paws, looking at viewer, smile, teeth, foreskin, white border, outside border, light pink background, simple background, gradient backgroundNote: The artist uses several well-known furry characters (cartoons, movies, comics, etc.), but in the training I left Lora flexible and malleable to be adapted / mixed with other Loras. My recommendation is that you use a character-specific Lora so that the final result is satisfactory.
Below is an initial configuration, but any other type of configuration is up to you:
ILLUSTRIOUS
Model
Illustrious XL personal merge (noob v-pred0.5 test merge updated) - v3.0_noob-1.0based
Lora
Freckles Style Lora v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 1)
Advanced
CFG Scale - 3.0 ~ 9.0 (Preferably 5)
Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)
Steps - 20 ~ 60 (Preferably 30)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by freckles, juniper (freckles), furry, furry female, intersex, gynomorph, anthro, animal ears, animal nose, snout, equine, horse, brown fur, white fur, body fur, two tone fur, white hair, long hair, huge ahoge, green eyes, huge breasts, nipples, sheath, fully sheathed, huge penis, huge testiles, muscular female, muscular intersex, ass, thick thighs, tail, 1girl, solo, completely nude, collarbone, stomach, smile, lips, looking at viewer, erection, veiny penis, standing, arm support, contrapposto, outside border, white border, dark yellow background, simple background, gradient backgroundPrompt (Negative)
bad quality, worst quality, worst detail, sketch, lowres, jpeg artifacts, signature, watermark, username, artist nameGeneral Observations:
If possible, give credit to the author Freckles while using this LoRA.
Do not sell or commercialize this LoRA.
Do not remove metadata from images generated by LoRA.
Description
About this version
More distant images may show some artifacts, distortions or disproportions in the face when generating images in Civitai, which is why the recommendation of this LoRA is to use characters closer to the image or use some Embedding / Face Fix to reduce errors in the face.
Example Images - (https://civitai.com/posts/26198049)
FAQ
Comments (9)
Ah yeah. Finally, a good freckles artstyle lora.
Thank you very much
Best lora for Freckles I've tried. Style is on point and his characters come out pretty accurate, even after stress testing it with complex prompts, kinks, themes...
Only errors I've ran across come mostly from tags overlapping with other concepts (Freckles with freckles, markings (socks) with actual socks, etc). I don't know how to mitigate it but I assume it's possible.
There's this weird issue of Soto's ear often having his markings green, for some reason?
Great release, will probably be my default choice if I ever want to make something in Freckles' style.
Thank you very much for the feedback. Regarding some points you highlighted (markings (socks)), I noticed that some models interpret them literally as socks or gloves. I also noticed that some models can't perfectly replicate a single-color character, so we have to resort to using a tag weight.
However, what I've noticed is that, generally, for this LoRa, NoobAI models perform better with prompt fidelity, even in CFG scales below 7, especially for characters.
@homer_26 I'm no expert, in fact rather new to this, so I don't know what do you exactly refer by tag weight and prompt fidelity.
I've tried doing small alterations like "markings (socks:0)", but that usually just puts me at square one, as if I had only typed "markings" in the prompt. I figure that's what you mean by tag weight?
I'll keep those in consideration however. I got lots to learn ever since I gave up genning in Civit and started doing it on my own PC.
@Spaghetti_C0D3 That's right, all tags have some weight in the prompt (almost hidden), but you can manually set the weight when you want to give the tag more prominence. For example, you can set:
(muscular male:1.7)
This means that of all the tags in the prompt, this "muscular male" has a weight of almost 2. Generally, the weight ranges from 0 to 2, and in between you can set "0.5" / "1.2" / "1.6" / "2".
Sometimes if you increase the weight too much, it can overshadow even a Lora and model and can "break" the image, generating artifacts or some kind of anomaly. With time and testing, you'll define it in your own way.
@homer_26 Oh right, then, yeah, I've been doing that for a while lol. Thanks!
HELL YEAH, another banger artstyle. This guy's style is a right pain in the ass to emulate without a lora on just about every model, glad to see this here
Thank you very much
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.
















