Model
Trends
.ai
Model
Trends
.ai
nejlepší open source AI modely
Spustit lokálně
illustriousXL_stabilizer_v1.72.safetensors
84 MB · SafeTensor
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
AD
<stabilizer-illus172-xl>
O tomto modelu
STABLE DIFFUSION XL 1.0 · LoRA
Vytvořil
reakaakasky
na Civitai
by reakaakasky - Stabilizer illustriousXL/NoobAI
Poznámky autora
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
5,771 stažení · 724 lajků na Civitai
SHA256
632563D18BB8782D889A44D6872D269BF567003FA8D9D6E286717F05EFF77AC9
ID modelu ModelTrends.ai
#11350
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Sampler
DPM++ 2M Karras
Kroky
25
Guidance
6
Seed
2129044405
Velikost
832x1216
Clip skip
2
Použitá váha
0.7
Prompt
score 9, score 8, score 7, masterpiece, best quality, gorgeous details, best aesthetics, perfect anatomy, perfect proportions, high resolution, anime illustration of a man, white border, white outline, 1 boy, male forum, solo, sad, serious, tears, colored hair, random hair color, random eye color, orange hair, black hair, multicolored hair, blue eyes, a mole under one eye, orange eyes, pastel colors, rainbow background, a multicolored hoodie with an iridescent gradient, fluffy ears, In his hands he holds a cardboard sign with the inscription "need_buzz" and heart , on which it says
Negativní prompt
(lowres:1.2), (worst quality:1.4), low quality, large head, extra digits, bad eyes, monochrome, bad hands, bad feet, fewer digits, extra digits, deformed, mutant, signature, artist name, ugly face, mutated hands, blurry face, blurry, fat, chubby, jpeg_artifacts, gif_artifacts, grainy, sketch, wip, uncolored, censored, scan, (female genitals, female genitalia, vagina, cunt, clit, breasts, feminine, 1girl, girl, female, woman:1.4 boobs, muscular, aged up, large muscular figure, beard
Nastavení
Sampler
Euler a
Kroky
20
Guidance
6
Velikost
2624x3840
Prompt
masterpiece, best quality, good quality, newest, highres, absurdres, 1girl, solo, highelfarcher, <lora:high-elf-archer-s2-ponyxl-lora-nochekaiser:1> high elf archer, long hair, green eyes, bow, hair bow, black bow, sidelocks, brown cloak, green hair, pointy ears, elf, thighhighs, boots, shorts, white sleeveless, bare arms, thigh boots, brown footwear, brown shorts ,closed mouth, upper body, looking to the side, gradient hair, leaf, pink flower, blue flower, Ethereal Brushstroke, borders, white borders, out of border Flat vector illustration, ((holding bow in hand)), bow and arrow, angry expression, aiming arrow, bow and arrow in foreground, perfect bow string, straight bwo string h4ra_illu, momosp <lora:illustriousXL_stabilizer_v1.23:0.3> <lora:NOOB_vp1_detailer_by_volnovik_v1:0.3> <lora:ponyv6_noobE11_2_adamW-000017:0.45> <lora:Illustrious:0.15> <lora:XXX667:0.75> <lora:checkpoint-e18_s306:1.3> <lora:hara_id_21:0.85> <lora:MomoSweetSpaceILL:0.8>
Negativní prompt
bad quality,worst quality,worst detail, censor, bad anatomy
Nastavení
Sampler
Euler a
Kroky
25
Guidance
6
Velikost
1280x1856
Použitá váha
0.6
Prompt
S4bit4mago_illu, anime style, s0wasow4rt_illu, masterpiece, newest, masterpiece, best quality, high quality, newest, highres, absurdres, <lora:sowasowart_style-000016:1>,score_9, score_8_up, score_7_up, concept, solo, extremely detailed, cartoon style, detailed background, detailed plants, thick outline, white outline, , rustic town, ivy growing, hydrangeas, many growing hydrangea, gothic fence framing, potted plants, doorway, quiet town, cobblestone, store front, balcony, cat, black cat, resting, masterpiece ,amazing quality, looking at viewer, intricate details, high quality, cute background,
Negativní prompt
bad quality, worst quality, worst detail, sketch, censor, worst quality, poorly drawn hands, animal, low res, patreon username, artist name, extra panels, comic bubble, blur, blurry, multiple characters, multiple views, cut in
Nastavení
Sampler
DPM++ 2M
Kroky
23
Guidance
1
Velikost
1664x2720
Prompt
1girl, solo, black hair, hair ornament, flower, wings, tattoo, makeup, rose, umbrella, ring, lipstick, eyeshadow, dragon, red lips, oil-paper umbrella, mechanical wings, steampunk
Negativní prompt
lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, old
Nastavení
Sampler
Euler a
Kroky
25
Guidance
6
Seed
1856143856
Velikost
832x1216
Clip skip
2
Použitá váha
0.6
Prompt
S4bit4mago_illu, anime style, s0wasow4rt_illu, masterpiece, newest, best quality, high quality, highres, absurdres, concept, extremely detailed, cartoon style, detailed plants, fluffy sheep wooloo, fluffy sheep mareep, sunny blue sky, blurry foreground, cloud, green field, horizontal pupils, mountain, no humans, on grass, outdoors, cute pokemon \(creature\), sheep, wooden fence, too many sheep, anime style flat color,
Negativní prompt
bad quality, worst quality, worst detail, sketch, censor, worst quality, poorly drawn hands, animal, low res, patreon username, artist name, extra panels, comic bubble, blur, blurry, multiple characters, multiple views, cut in
Nastavení
Sampler
DPM++ 2M
Kroky
20
Guidance
6
Velikost
1664x2720
Prompt
1girl, solo, short hair, black hair, upper body, flower, glasses, blunt bangs, lips, headphones, round eyewear
Negativní prompt
lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, old, extra_fingers, malformed_hands, deformed_feet
Nastavení
Sampler
Euler a
Kroky
20
Guidance
6
Velikost
1664x2720
Prompt
1girl, solo, long hair, looking at viewer, blush, shirt, skirt, black hair, long sleeves, closed mouth, jewelry, brown eyes, school uniform, white shirt, full body, ponytail, weapon, pleated skirt, shoes, socks, serafuku, sword, black skirt, sailor collar, black footwear, grey background, lips, gradient background, kneehighs, squatting, black socks, katana, black nails, sheath, sheathed, shirt tucked in
Negativní prompt
lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, old, extra_fingers, malformed_hands, deformed_feet
Nastavení
Sampler
Euler a
Kroky
25
Guidance
6
Velikost
1280x1856
Použitá váha
0.6
Prompt
(sparkling eyes), S4bit4mago_illu, anime style, s0wasow4rt_illu, halftone, detailed background, , Cartoon_Type, score_9, score_8_up, score_7_up, (solo), extreme detail, masterpiece, best quality, amazing quality, very aesthetic, high resolution, fluffy fur, ultra-detailed, absurdres, (beautiful moth girl), 1 girl, close up, fluffy, (compound eyes), from side, looking up at sky, behind trees, bug_like eyes, dynamic angle, from above, anthro, ((cute theme)), source_anime, large black eyes, body covered, reaching for snow, (falling snow), snowflake in hand, snow in foreground, depth of field, looking into distance, trees in forground, snowy forest, in foliage, soft smile, wearing cloak, curvy, glossy body, puzzled look, dynamic angle, sparkling eyes, glitter eyes,
Negativní prompt
bad quality, worst quality, worst detail, sketch, censor, worst quality, poorly drawn hands, low res, patreon username, artist name, blur, blurry, multiple characters, nudity
AI modely pro generování obrázků, videa a textu
stabilizer illus172 xl je LoRA pro rodinu Stable Diffusion XL 1.0 uvedený na ModelTrends.ai, katalogu open source AI modelů pro obrázky, video a text určeném jen ke čtení. Porovnejte ho s dalšími modely Stable Diffusion XL 1.0, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Procházet podle rodiny modelů
Procházet všechny modely