Model
Trends
.ai
Model
Trends
.ai
de bästa AI-modellerna med öppen källkod
Kör lokalt
noobai_ep10_stabilizer_v0.273_fp16.safetensors
43 MB · SafeTensor · fp16
Nedladdningar sköts av Civitai. Vissa skapare kräver att du först loggar in på Civitai.
AD
<stabilizer-nbep10-xl>
Om denna modell
STABLE DIFFUSION XL 1.0 · LoRA
Skapad av
reakaakasky
på Civitai
by reakaakasky - Stabilizer IL/NAI
Skaparens anteckningar
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
3,282 nedladdningar · 354 gillningar på Civitai
SHA256
C4E5893CE1857AD7E85B9DC5FFB3FF526602FB7E7B44508C62C3BD8939B07E84
ModelTrends.ai modell-ID
#17086
Rapportera innehåll
Exempelrenderingar
Prompter och inställningar delade av personerna som gjorde dessa renderingar på Civitai. Välj en rendering för att se hur den gjordes.
Inställningar
Sampler
Euler a
Steg
30
Guidance
3
Seed
254656421082242
Storlek
3584x4608
Clip skip
2
Använd vikt
0.4
Prompt
columbina \(genshin impact\), 1girl, lazypos, (hyper detailed), japanese anime style, volumetric light, sharp focus, focused subject, intricate details, soft lighting, clean lines, dynamic angle, natural lighting, addmicrodetails, Enchanting Eyes, perfect face, perfect eyes, hyper detailed eyes, looking at viewer, shy, coy, detailed iris, eye focus, dark_eye_focus, normal hand, upper body, medium breasts, perfect body, long hair, dynamic pose, japanese yukata, trot, extra long sleeves, japanese summer festival, scnr, sensitive,
Negativ prompt
lazyloli, lazyneg, bad quality, worst detail, normal quality, out of focus, bad composition, jpeg artifacts, noise, overexposed, underexposed, oversaturated, bad lighting, deformed, cropped, duplicate, poorly drawn face, cloned face, lazyhand, bad hand, ribs, mole, sex, spread anal, veins, long body, blush, nipples, (lazynsfw:0.2),
Inställningar
Sampler
Euler a
Steg
30
Guidance
3
Seed
316005739680859
Storlek
3808x4896
Clip skip
2
Använd vikt
0.4
Prompt
columbina \(genshin impact\), 1girl, lazypos, (hyper detailed), japanese anime style, volumetric light, sharp focus, focused subject, intricate details, soft lighting, clean lines, dynamic angle, natural lighting, addmicrodetails, Enchanting Eyes, perfect face, perfect eyes, hyper detailed eyes, close eyes, smile, detailed iris, eye focus, dark_eye_focus, normal hand, full body, medium breasts, perfect body, long hair, dynamic pose, white flowing dress, dance, extra long sleeves, night, moon, white flower sea, scnr, sensitive,
Negativ prompt
lazyloli, lazyneg, bad quality, worst detail, normal quality, out of focus, bad composition, jpeg artifacts, noise, overexposed, underexposed, oversaturated, bad lighting, deformed, cropped, duplicate, poorly drawn face, cloned face, lazyhand, bad hand, ribs, mole, sex, spread anal, veins, long body, blush, nipples, (lazynsfw:0.2),
Inställningar
Sampler
Euler a
Steg
30
Guidance
3
Seed
489222873722890
Storlek
3584x4608
Clip skip
2
Använd vikt
0.4
Prompt
collei \(genshin impact\), 1girl, lazypos, (hyper detailed), japanese anime style, volumetric light, sharp focus, focused subject, intricate details, soft lighting, clean lines, dynamic angle, natural lighting, addmicrodetails, Enchanting Eyes, perfect face, perfect eyes, hyper detailed eyes, looking at viewer, shy, coy, detailed iris, eye focus, dark_eye_focus, normal hand, upper body, medium breasts, perfect body, long hair, dynamic pose, japanese yukata, trot, (cat ears), airplane ears, flattened ears, extra long sleeves, japanese summer festival, scnr, sensitive,
Negativ prompt
lazyloli, lazyneg, bad quality, worst detail, normal quality, out of focus, bad composition, jpeg artifacts, noise, overexposed, underexposed, oversaturated, bad lighting, deformed, cropped, duplicate, poorly drawn face, cloned face, lazyhand, bad hand, ribs, mole, sex, spread anal, veins, long body, blush, nipples, (lazynsfw:0.2),
Inställningar
Sampler
Euler a
Steg
30
Guidance
3
Seed
97263255539571
Storlek
3808x4896
Clip skip
2
Använd vikt
0.4
Prompt
columbina \(genshin impact\), 1girl, lazypos, (hyper detailed), japanese anime style, volumetric light, sharp focus, focused subject, intricate details, soft lighting, clean lines, dynamic angle, natural lighting, addmicrodetails, Enchanting Eyes, perfect face, perfect eyes, hyper detailed eyes, looking at viewer, smile, detailed iris, eye focus, dark_eye_focus, normal hand, full body, medium breasts, perfect body, long hair, dynamic pose, white flowing dress, night, moon, white flower sea, extra long sleeves, japanese summer festival, scnr, sensitive,
Negativ prompt
lazyloli, lazyneg, bad quality, worst detail, normal quality, out of focus, bad composition, jpeg artifacts, noise, overexposed, underexposed, oversaturated, bad lighting, deformed, cropped, duplicate, poorly drawn face, cloned face, lazyhand, bad hand, ribs, mole, sex, spread anal, veins, long body, blush, nipples, (lazynsfw:0.2),
Inställningar
Sampler
Euler a
Steg
29
Guidance
4
Seed
1507811365
Storlek
832x1216
Clip skip
2
Använd vikt
0.3
Prompt
masterpiece, absurdres, 8k, insanely detailed, sharp focus, high detail, Smooth, sharp lines, detailed, masterpiece, close up, very close up, BREAK , S-Snake, 1girl, dark-skinned female, white hair, long hair, earrings, black wings, feathered wings, BREAK , standing, floating, legs together, sky, clouds, open wings, serious face, sun, open arms, open hands, arms up, small breast, white dress, BREAK,
Negativ prompt
(worst quality, bad quality:1.2), lowres, bad anatomy, worst detail, sketch, censored, watermark, signature, artist name, old, oldest,
Inställningar
Sampler
Euler a
Steg
30
Guidance
3
Seed
972136659238250
Storlek
3584x4608
Clip skip
2
Använd vikt
0.4
Prompt
akashi \(azur lane\), 1girl, lazypos, (hyper detailed), japanese anime style, volumetric light, sharp focus, focused subject, intricate details, soft lighting, clean lines, dynamic angle, natural lighting, addmicrodetails, Enchanting Eyes, perfect face, perfect eyes, hyper detailed eyes, looking at viewer, smile, detailed iris, eye focus, dark_eye_focus, normal hand, upper body, medium breasts, perfect body, long hair, dynamic pose, japanese yukata, trot, (extra long sleeves:1.5), japanese summer festival, scnr, sensitive,
Negativ prompt
lazyloli, lazyneg, bad quality, worst detail, normal quality, out of focus, bad composition, jpeg artifacts, noise, overexposed, underexposed, oversaturated, bad lighting, deformed, cropped, duplicate, poorly drawn face, cloned face, lazyhand, bad hand, ribs, mole, sex, spread anal, veins, long body, blush, nipples, (lazynsfw:0.2),
Inställningar
Sampler
Euler a
Steg
30
Guidance
3
Seed
598363045920758
Storlek
3584x4608
Clip skip
2
Använd vikt
0.4
Prompt
collei \(genshin impact\), 1girl, lazypos, (hyper detailed), japanese anime style, volumetric light, sharp focus, focused subject, intricate details, soft lighting, clean lines, dynamic angle, natural lighting, addmicrodetails, Enchanting Eyes, perfect face, perfect eyes, hyper detailed eyes, looking at viewer, smile, detailed iris, eye focus, dark_eye_focus, normal hand, upper body, medium breasts, perfect body, long hair, dynamic pose, japanese yukata, trot, cat ear, extra long sleeves, japanese summer festival, scnr, sensitive,
Negativ prompt
lazyloli, lazyneg, bad quality, worst detail, normal quality, out of focus, bad composition, jpeg artifacts, noise, overexposed, underexposed, oversaturated, bad lighting, deformed, cropped, duplicate, poorly drawn face, cloned face, lazyhand, bad hand, ribs, mole, sex, spread anal, veins, long body, blush, nipples, (lazynsfw:0.2),
Inställningar
Storlek
896x1152
Prompt
1girl,solo,tamamo \(fate\),long hair,hands in pockets,white coat,pantyhose,standing,from behind,from below,fox tail,wind,moon in sky,night,stars,galaxy,cosmic,space,ruins,skyscraper,burning building,fire sparkle,cinematic,lens flare,cowboy shot,masterpiece,
AI-modeller för bild-, video- och textgenerering
stabilizer nbep10 xl är en LoRA för familjen Stable Diffusion XL 1.0, listad på ModelTrends.ai, en skrivskyddad katalog över AI-modeller med öppen källkod för bild, video och text. Jämför den med andra Stable Diffusion XL 1.0-modeller, se dess hettapoäng och prova den på PirateDiffusion eller BitVector.
Bläddra efter modellfamilj
Bläddra bland alla modeller