Run Locally
krea2_furry_0716.safetensors
327 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
KREA2 · LoRAs
by hxyy - krea2 furry
Creator notes
The model was trained on approximately 1600 images of various types. To ensure versatility, it was trained on multiple styles, and secondary images were assigned lower probabilities.
Approximately 25% of the main data consisted of fursuits. The rest were images of various different styles.
NSFW training was conducted, but the interweaving of different concepts and the varying learning difficulty make it unreliable compared to dedicated models.
Due to the limitations of the device's memory, the training resolution was set at 512.
The intensity can range from approximately 0.2 to 1.5.
Some display images:
Sampler
er_sdr can obtain more detailed images.
euler/a is more stable.
If you want to obtain better details/quality, use multi-level sampling and switch the sampler.
Training tool: OneTrainer
Rank: 48
If you wish to continue training this model with new data, this setup should allow you to do so; other parameters should not hinder the training process.
If you need better, smoother fur textures, you can use the raw model.
如果你需要更好更细腻的皮毛纹理,可以使用raw模型
====
模型在约1600张多种类型的图像上训练,为了泛用性在多种风格上训练,但次要图像使用更低的概率。
主要数据中大约25%是fursuit。其它是各种不同风格的图像。
进行了NSFW训练,但是不同概念之间相互交错和学习难度不同,与专用模型相比并不可靠。
受限于设备显存,训练分辨率为512。
强度可以在大约0.2~1.5生效。
采样:
er_sdr 获得更多细节
euler/a 更稳定
如果你想获得更好的细节/质量,使用多级采样和切换采样器.
训练工具:OneTrainer
rank:48
如果你想在此模型上使用新数据继续训练,这应当能能让你继续,其它参数应该不会阻止训练
Trigger words
fursuit
realistic fursuit
kemono fursuit
toony fursuit
anthro
furry
kemono
digital painting
anime style
SHA256
ADCD03CD80EE6EFE0229FD8E67B9844DA8A516DAD03D37A1BAB074FB07FBDE15
ModelTrends.ai Model ID
#26609
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler
Steps
40
Guidance
7
Seed
863247983
Size
1920x3456
Weight used
0.7
Prompt
A moody, cinematic 35mm portrait captured through a tight close-up shot through the heavily scratched, weathered glass pane of an aging, rusted red public telephone booth at an abandoned rural crossroads. Inside the booth, a weary anthropomorphic snow leopard green eyes wanderer with elegant golden-grey fur and dark-grey spots, rendered in a delicate anime style with clean linework and soft cel shading, wears a pair of black-framed glasses. He holds the dusty rotary phone receiver to his ear, his eyes slightly narrowed and tired behind the lenses, brow slightly furrowed in deep, weary concentration as if receiving a long-awaited or unsettling call. The camera is positioned slightly below eye level, creating a dramatic, slightly downward-looking perspective that emphasizes his solitary stance against the heavy, fogged glass. Outside, the dying rays of an amber sun cast sweeping horizontal light leaks across the glass. The golden backlighting carves a sharp, radiant rim light along his jaw and pointed ears, while the booth's dark interior is wrapped in heavy analog film grain, nostalgic vignetting, and deep velvety shadows. Ghostly reflections of a faded, empty evening sky and the worn, peeling paint of the booth interior are layered on the scratched glass itself, creating a double-exposure effect over his anime-style silhouette. The overall palette is drenched in rich sepia and warm amber tones, evoking a bittersweet, deeply nostalgic memory.
Settings
Sampler
Euler
Steps
8
Guidance
1
Seed
990310142755562
Size
1088x1856
Prompt
A poetic cinematic 85mm portrait capturing human and creature symbiosis in an ancient enchanted glade. A handsome young human prince in flowing emerald and gold Hanfu extends his hand forward toward the lens in sharp foreshortening, while resting his cheek against the majestic head of a colossal white tiger guardian. The white tiger gazes forward with profound, glowing aquamarine-blue eyes, its silver whiskers and the boy’s long black hair tangled together in the wind. Intricate forest leaf shadows dance across their touching faces, accented by shimmering golden pollen, floating rainbow cicada wings, and soft volumetric light rays piercing the misty canopy.
Settings
Sampler
Euler
Steps
8
Guidance
1
Seed
4218773308
Size
1976x1440
Prompt
A detailed digital comic.
the setting is a goth bedroom, with purple wallpaper, a "Sisters of Mercy" band posters on the wall and a partially visible bed with black sheets. it is night, the moon is visible through a window.
Tabitha, a goat girl furry with white fur, short black hair with bangs, goat ears, brown goat horns, red eyes and medium breasts. She is wearing an oversized black tshirt that leaves one shoulder exposed, reaching to her knees. worn on her neck a black choker with a silver heart pendant. She is holding a flashlight and has a confused expression as she is looking under the bed. She has a speech bubble. "I'll pretend I just didn't see that..."
under the bed is an adorable tiny pink monster with big yellow eyes, pointy teeth and a scared expression, holding a bongo drum.
The atmosphere is raunchy, funny and erotic. <lora:krea2_furry_0716:0.7> <lora:Krea2_TextFusion_Refusal_Reduction_v2:1>
Negative prompt
worst quality, low quality, bad quality, bad hands, missing finger, extra fingers, wolf tail, size difference
Settings
Sampler
Euler
Steps
12
Guidance
1
Seed
784443200261480
Size
1440x1920
Prompt
Safe, sfw image. Medieval style, super slim, 2 women - Argonian green lizard woman and Khajiit yellow feline woman with human body shape.
An internet meme in a digital comic style. A view from behind of a human character (wearing the iron horned helmet), standing at a fork in a dirt road in a grassy field. There are two paths. On the left side, a path leads to a slim female Khajiit girl (a yellow-furred cat person with blue eyes and ear ring, her body is sand-yellow colored, 4 toes, small black claws) wearing a white wedding dress and veil, holding a bouquet of roses, looking cute. On the right side, a path leads to a female Argonian (a green-skinned lizard person with yellow eyes and two white horns, 3 toes, large black talons) wearing a black and white maid outfit, holding a baked loaf on a tray, looking cute. At the top of the image, white text on a black background reads: "Which way True son of Skyrim?". Both female look very slim and cute, both are tall, have long legs. Both are looking at viewer with blushing, both are digitigrade. Their clothes are modest. Looking at viewer.
Negative prompt
nsfw, explicit, erotic
Settings
Sampler
er_sde
Steps
12
Guidance
1
Seed
222859483873151
Size
1024x1536
Prompt
2d, geffstyle,
1girl, solo, looking at viewer, smile, dress, holding, animal ears, jewelry, green eyes, tail, full body, red hair, teeth, grin, blue dress, colored skin, sandals, sharp teeth, freckles, mouse ears, labcoat, mouse tail, hammer, mallet, digitigrade, paws, cute, blue shorts,
Digital drawing of an anthro mouse girl with white fur on her body, red fur on her tail and ears. She has long red hair, green eyes, sharp teeth in a wide grin, and is wearing a blue dress with a green pendant, a white lab coat, and black sandals. She holds a large hammer over her right shoulder with both hands. The background is a gradient of light to dark green with vertical lines.
Settings
Sampler
Euler
Steps
8
Guidance
1
Seed
75063771851145
Size
1216x1664
Prompt
A grandiose dark anime masterpiece combining rough charcoal paint smudges and heavy oil impasto textures, depicting a battle-worn male tiger anthro in tattered dark samurai robes facing ghostly digital phantoms. Shot from a wide dramatic Dutch-angle with strong perspective distortion, his glowing golden eyes blaze with fierce intensity as cold white spiritual energy flashes around his drawn katana, creating dynamic motion blur ghosts and dispersing particle sparks. The color palette is composed of desaturated midnight blue, charcoal black, and desaturated violet gradients, laced with red light leaks. Heavy ISO 400 film noise, intense chromatic aberration, and severe VHS digital glitches tear across the canvas, embodying a wild, existential struggle against oblivion.
Settings
Sampler
Euler a_simple
Steps
8
Guidance
1
Seed
381518288831585
Size
1664x2432
Clip skip
2
Prompt
A dramatic, dynamic anime-style fantasy illustration of an anthropomorphic mouse girl rogue standing barefoot on wet cobblestones in a misty, foreboding forest path at night, her soft sand-brown and cream fur glowing faintly under the warm amber light of a brightly glowing brass oil lantern she holds in one outstretched hand, casting long, sharp shadows across the damp stones; her other hand drawn tight with a steel shortsword poised for defense, dressed in traveler’s clothes including wide-leg ranger trousers, a layered tunic, a purple sash, and leather utility pouches, her prominent rounded mouse ears poking through a dark navy hooded mantle, whiskers twitching, and big expressive dark eyes filled with resolve as she gazes forward; blurred background with bokeh effect, deep fog swirling around her, and far away behind her in the dark mist a black blurred silhouette of a colossal feral owl figure looming in the far distance, all rendered in high fantasy adventure aesthetic with rich storytelling, intense atmospheric lighting, and cinematic depth, framed to emphasize her solitary courage against the encroaching wilderness. <lora:Krea2_TextFusion_Refusal_Reduction:1> <lora:krea2_ta86_inkriot_V2:0.5> <lora:FurryToonMix_krea2:0.4> <lora:furry_enhancer_Krea2V2.1:0.6> <lora:krea2_furry_0716:0.75>
Negative prompt
blurry, lowres, pixelated, low quality, worst quality, jpeg artifacts, noise, grain, compression, chromatic aberration, out of focus, plastic skin, blurry, lowres, pixelated, low quality, worst quality, jpeg artifacts, noise, grain, compression, chromatic aberration, out of focus, plastic skin,waxy skin, over-saturated colors, warped anatomy, smeared details, over-processing, composite look
AI Models for Image, Video & Text Generation
furry krea2 is a LoRA for the Krea2 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Krea2 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
