Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
illustriousXL_stabilizer_v1.23.safetensors
61 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<stabilizer-illus123-xl>
About This Model
STABLE DIFFUSION XL 1.0 · LoRAs
Created by
reakaakasky
on Civitai
by reakaakasky - I named this LoRA "stabilizer" because in the first few versions I just want to make NoobAI have a stable style. But now it can do more than that. So just forget about the name. It can improve character's overall details, natural lighting, brightness, contrast, anti oversaturation, ...many things... Unlike concept/strong style LoRAs. This LoRA was not overtrained/overfitted. It will not dramatically change the model output. In other words, it can retain 100% of the creativity of the base model. You won't get fixed poses and backgrounds and objects etc. This also means it has very good compatibility. Use a weight as low as 0.4 to 0.8.
Creator notes
Stabilizer Name is misleading. This is NOT a LoRA that can magically fix your overfitted merged base model. This is a finetuned model from pretrained model. But trained as a LoRA. - 11k images. No bias, no default style. - Zero smooth plastic glossy AI image in dataset. Glossy Al images are polluting the world, but not on my watch, I handpicked every single image. - Natural language captions from Gemini, rather than tags in random order with high FPR. - Standard noise scheduler. Inpainting/img2img friendly. Improvements: You can get the style exactly as it should be (as long as the model knows). Comparisons with pretrained base model: - (general styles, you get the style exactly as it should be) - (artist styles, no style shifting because this model does not have bias) See more xy plots in cover images. Why LoRA? - This LoRA is a (from Nvidia), which is more efficient than traditional LoRA. - Enough for thousands of training images. - What? You prefer to download and store a 7GiB checkpoint than a 80Mib LoRA? Share merges using this model is prohibited. FYI, there are hidden trigger words to print invisible watermark. I coded the watermark and detector myself. I don't want to use it, but I can. This model only published on Civitiai and TensorArt. If you see "me" and this sentence in other platforms, all those are fake and the platform you are using is a pirate platform. How to use It is highly recommended that you use pretrained base model. And load this LoRA with strength 1. Versions: - cknb (). - nbvp10 (). FYI: you don't need CFG hacks (RescaleCFG etc.). - nbep10 (). - illus01 (Illustrious v0.1). Load this LoRA first This LoRA uses a new arch called from Nvidia, more efficient than traditional LoRA. But the patch weight is dynamically calculated based on the currently loaded base model weights (which will be changed when you loading other LoRAs). To avoid unexpected changes, load this LoRA first. Specify styles in prompt This model does not have an strong default style and is very creative. You must specify the style you want in the prompt. If you want to use it on finetuned/merged base models: I personally disagree this. This is not the model's original intention. But this is a LoRA after all. Be aware: This LoRA can't remove glossy shiny plastic AI style. Although the dataset is "AI image free". It can't make AI image polluted 1girl overfitted 50 versions of Nova furry 3D anime WAI or whatever look better. What the model learned is learned. Use a pretrained base model if you want to get rid of overfitted AI style. What is "overfitted AI style"? This is what Craft Lawrence (from spice and wolf) should be, if you've seen the anime: . This is what those AI style polluted 1girl overfitted model generated: Some base models already merged this model. If you got deformed images with this LoRA even at low strength (e.g. <0.5). Your base model has already merged this LoRA (and you merged it twice). And the model weights got multiplied (because how the works) and collapsed. Beware of fake base model creators, aka. thieves. Some "creators" never do the training, they only grab other people's models, merge them, wipe all metadata and credits, and sell it as their own base model. Update log Moved
18,661 downloads · 2,702 likes on Civitai
SHA256
A2EFEE207AB7C8A943B34E0A4E26D52C2BEF6F9543709627ACF5497B039B26A8
ModelTrends.ai Model ID
#17970
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
DPM++ 2M Karras
Steps
20
Guidance
6
Seed
4294967295
Size
832x1216
Clip skip
2
Weight used
0.3
Prompt
masterpiece, best quality, good quality, very awa, newest, highres, absurdres, 1girl, solo, dress, standing, flower, outdoors, water, white flower, pink flower, scenery, reflection, rain, dark, ripples, yellow flower, puddle, colorful, abstract, standing on very Wide Shot, limited palette
Negative prompt
lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, old
Settings
Sampler
Euler a
Steps
19
Guidance
3
Seed
1798821172
Size
832x1216
Clip skip
2
Weight used
0.4
Prompt
Masterpiece, best quality,amazing quality,very aesthetic, high resolution, dynamic pose,solo, black background, blank background, full body, high detail, Smooth, detailed, masterpiece, masterwork, super cute style, Masterpiece, best quality,amazing quality,very aesthetic, high resolution, Masterpiece, best quality, amazing quality, very aesthetic, high resolution, dynamic pose, solo, black background, simple background, white outline, sticker_style, gold details, c0t0n0_illu, u3nomigi_illu, abstract, abstract shapes, halftone, blue cat ears, blue cat tail, (blue skin: 1.4), colored skin, yellow eyes, cat pupils, dark blue hair, medium hair, bobcut, doll joints, bored, jitome, black eyeshadow, flat breasts, medium hips, short, dark blue ears, dark blue tail, gold inner ear, gold details, thief cloak, fur trim, long sleeve tunic, belt, purse, black leggings, boots, long gloves, long boots, skirt, dirty clothes, dark clothing, brown and black clothes, thick clothes, bracers, rogue, thief, hood down, thick gloves, gold forearm bracers, holding dagger,dirk dagger, attack,dagger, holding dagger, attack, lunge,EminemThrowingMeme,motion lines, motion blur,throwing,(throwing object:1.2), fullcolor, blurred lineart,(((wagashi))), messy hair,((dagashiya)),iwako,Chillof Vorn'thar, Crystal Blade, crystal dagger background,Cartoon style, fullcolor, blurred lineart, no background, , S4bit4mago_illu
Negative prompt
lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, bad perspective, bad proportions, (bad hands,extra fingers, extra digits), (((human_ears, multiple ears)))
Settings
Sampler
Euler a
Steps
15
Guidance
2.5
Seed
1148469790
Size
832x1216
Clip skip
2
Weight used
0.4
Prompt
rain, rainbow, multiple cats, domestic cat, four cats, orange tabby cat, calico cat, black tabby cat, white tabby cat, striped kitten, on rooftop, sitting in a row, back view, tail hanging down, tail down, sunny day, soft shadows, warm lighting, vibrant colors, slice of life, serene_mood, bluesky, white clouds, urban rooftop, concrete wall, plants in foreground, tree, open air, peaceful afternoon, masterpiece, amazing quality, best quality, scenery, painterly, anime coloring
Negative prompt
lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, bad perspective, bad proportions, (bad hands,extra fingers, extra digits),
Settings
Sampler
DPM++ 2M
Steps
30
Guidance
7
Seed
1209350
Size
2624x3840
Weight used
0.3
Prompt
safe_pos, source_anime, high res image, (masterpiece:1.2), best quality, very awa, absurdres, perfect quality, newest, highres, (4k, 8k, Ultra HD), (ultra-detailed:1.2), very aesthetic, sharp focus, depth of field, ray tracing, best lighting, detailed illustration, detailed background, scenic, cinematic, glowing particles, shinny, glitter, BREAK konpaku youmu, 1girl, solo, white hair, short hair, blunt bangs, blue eyes, hairband, hair ribbon, black ribbon, black bowtie, white shirt, collared shirt, green vest, green skirt, socks, beautiful face, beautiful eyes, detailed eyes, glossy lips, glossy hair, (full body:1.1), (release particles light:1.1), (floating particle light:1.1), purple glowing aura body, purple magic array, accurate anatomy, ultra detailed face, luminous ghost, BREAK katana, (detailed katana:1.2), sheath, drawing a katana, unsheathing a katana, (battoujutsu stance:1.1), dynamic pose, fighting stance, ready to draw, BREAK cherry blossom tree, cherry blossoms, blowing in the wind, windy, midnight, dark background, moon light, (soft lighting:1.1), stars, pastel colors, gradient color, tense atmosphere, warm tone, soft fill light, (ambient light), (dynamic light), vivid colors, high contrast, bright face, illuminated face, cinematic angle, dutch angle, dynamic angle
Negative prompt
safe_neg, source_cartoon, 3d, low res, interlocked fingers, anatomically incorrect hands, pony, furry, oldest, censored, (censor), anatomical nonsense, low quality, blurry, bad anatomy, worst quality, text, watermark, normal quality, ugly, signature, deformed, extra limbs, disfigured, jpeg artifacts, bad hands, error, mutation, missing fingers, poorly drawn hands, poorly drawn face, monochrome, extra digit, fewer digits, extra fingers, mutated hands, extra legs, extra arms, bad proportions, easynegative, fused fingers, missing arms, duplicate, mutated, missing legs, too many fingers, mutilated, malformed limbs, gross proportions, cloned face, bad art, grayscale, bad quality, lowres
Settings
Sampler
res_multistep_kl_optimal
Steps
30
Guidance
4
Seed
906966760796694
Size
768x1280
Clip skip
2
Prompt
masterpiece, best quality, amazing quality, klskx, nsfw, explicit, 1girl, lisa \(genshin impact\), hat, seductive smile, playful expression, latex bodysuit, corset, (from side:0.9), standing on one leg, (cameltoe:0.9), v over eye, book in hand, indoors, (grand library:1.2), wooden bookshelves, scattered open books, dim candlelight, luxurious furniture, (dark shadows:0.9), (high contrast:0.9), volumetric lighting, intricate details, blurry background, depth of field <lora:spo_sdxl_10ep_4k-data_lora_webui:2.0> <lora:illustriousXL_stabilizer_v1.23:1.0> <lora:illustrious_quality_modifiers_masterpieces_v1:0.6> <lora:klskx_wai:0.7000000000000001>
Negative prompt
loli, bad quality, worst quality, sketch, censored, watermark, signature, blurry, plain simple background, blank eyes, hydrokinesis, symmetry, huge breasts, dust particles in air, thighhighs,
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
6
Seed
4971662076
Size
832x1536
Clip skip
2
Prompt
masterpiece, best quality, good quality, very awa, newest, highres, absurdres, outdoors,tree, no humans, shadow, traditional media, scenery, nature, motor vehicle, forest, bubble, car, road, one-eyed, horror \(theme\), eye focus, ink \(medium\), (looking down:1.2), limited palette, sketch, glowing, psychedelic, <lora:illustriousXL_stabilizer_v1.23:0.3> <lora:NOOB_vp1_detailer_by_volnovik_v1:0.3> <lora:ponyv6_noobE11_2_adamW-000017:0.3> <lora:114558v4df2fsdf5:0.7> <lora:mon_monmon2133:0.8>
Negative prompt
lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, old
AI Models for Image, Video & Text Generation
stabilizer illus123 xl is a LoRA for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 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
Browse all models