Model
Trends
.ai
Model
Trends
.ai
nejlepší open source AI modely
Spustit lokálně
Sy3.safetensors
72 MB · SafeTensor
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
AD
<bubble-drip>
O tomto modelu
STABLE DIFFUSION 1.5 · LoRA
Vytvořil
LDWorksDavid
na Civitai
__html__Hi again and welcome to the Bubble world!"Bubble Drip" is an experimental LORA that will create a very specific Bubblish-background dripping style. This version focus on orange/blue color scheme as it was created for testing purposes but turned out very flexible so, here it is.Token is: Sy3 (and nope, its not related to an artist or something, was to put a token trigger).How to prompt*****************See the examples attached but:1) Portrait/close up portrait/landscape/etc. of a [concept] in the style of Sy32) Cose up of a portrait/landscape/etc. of a [concept] in the style of Sy33) A [concept] in the style of Sy3Of course you can decide to not put Sy3 but putting the Token will summon the effect easier. And you can always weight it if it's too much and so on.Caution when using negative embeddings as easynegative and so on. I'd recommend to use it on a normal basis though.Recommended values & models*************************************Didn't test on every model but AnyLora, RevAnimated and DreamShaper works.For values if you use Token 0.7-01 are the values to go and when not using Token 0.8-1 are good values (and in certain cases it handles till 1.2).Quick tip: Don't forget you can use "halfs" (0.85, 0.75, etc.).This LORA is GOOD for:***************************- Poster/vectorized works- Graphic design works.- Portraits/landscapes- Abstract/graffiti aesthetics in BG- Subtle drip effects playing with strenghtIMPORTANT!I wrote an article here and it's like my finetunning
Poznámky autora
Hi again and welcome to the Bubble world! "Bubble Drip" is an experimental LORA that will create a very specific Bubblish-background dripping style. This version focus on orange/blue color scheme as it was created for testing purposes but turned out very flexible so, here it is. Token is: Sy3 (and nope, its not related to an artist or something, was to put a token trigger). How to prompt ***************** See the examples attached but: 1) Portrait/close up portrait/landscape/etc. of a [concept] in the style of Sy3 2) Cose up of a portrait/landscape/etc. of a [concept] in the style of Sy3 3) A [concept] in the style of Sy3 Of course you can decide to not put Sy3 but putting the Token will summon the effect easier. And you can always weight it if it's too much and so on. Caution when using negative embeddings as easynegative and so on. I'd recommend to use it on a normal basis though. Recommended values & models ************************************* Didn't test on every model but AnyLora, RevAnimated and DreamShaper works. For values if you use Token 0.7-01 are the values to go and when not using Token 0.8-1 are good values (and in certain cases it handles till 1.2). Quick tip: Don't forget you can use "halfs" (0.85, 0.75, etc.). This LORA is GOOD for: *************************** - Poster/vectorized works - Graphic design works. - Portraits/landscapes - Abstract/graffiti aesthetics in BG - Subtle drip effects playing with strenght IMPORTANT! I wrote an article and it's like my finetunning diary for the ones interested with releases upcoming, trainings done, exclusive patreon models previews, personal thoughts, etc. So if you want to see what I'm planning or what I'm into, feel free to take a look. Enjoy and don't forget you can support me and my pal in our  so we can keep creating more and better content. David.
Spouštěcí slova
Sy3
8,395 stažení · 1,597 lajků na Civitai
SHA256
C9F643A52CFEED29E0EFA6699AF5756B3B01571287741FDED79D83828AB63401
ID modelu ModelTrends.ai
#8779
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Sampler
DPM++ SDE Karras
Kroky
14
Guidance
7.5
Seed
2060676230
Velikost
512x768
Clip skip
2
Prompt
<lora:Sy3:0.7> saturn in the style of sy3
Negativní prompt
easynegative
Nastavení
Sampler
Euler a
Kroky
20
Guidance
7
Seed
3970782506
Velikost
1024x1536
Clip skip
2
Prompt
(best quality, masterpiece, RAW photo,ultra-detailed:1.2), <lyco:GoodHands-beta2:1.0>,cat,solo,looking at viewer, <lyco:Sy3:1> sy3,
Negativní prompt
(worst quality, low quality), bad_pictures, negative_hand-neg,
Nastavení
Sampler
DPM++ SDE Karras
Kroky
14
Guidance
7
Seed
2258170680
Velikost
512x512
Clip skip
2
Prompt
<lora:Sy3:1> a house
Negativní prompt
easynegative
Nastavení
Sampler
DPM++ SDE Karras
Kroky
14
Guidance
5.5
Seed
4032918374
Velikost
512x768
Clip skip
2
Prompt
<lora:Sy3:1> portrait, male, wizard, short red hair, sitting
Negativní prompt
easynegative
Nastavení
Sampler
DPM++ 2M Karras
Kroky
20
Guidance
7
Seed
3767393822
Velikost
1024x1536
Clip skip
2
Prompt
Superman Portrait , ((blue)) background ,Sy3,
Negativní prompt
16-token-negative-deliberate-neg, easynegative , By bad artist -neg
Nastavení
Sampler
DPM++ 2S a Karras
Kroky
30
Guidance
7
Seed
2640592821
Velikost
512x768
Prompt
clown, fantasy creature, Sy3, <lora:Sy3:.9> Best quality, masterpiece, ultra high res, absurdres,
Negativní prompt
easynegative, logo, watermark, text, (worst quality:1.5), (low quality:1.5), (normal quality:1.5), low res, bad anatomy, bad hands, normal quality, black and white photos,(monochrome), (grayscale), Sy3, <lora:Sy3:.9> Best quality, masterpiece, ultra high res, absurdres, ", Hires upscale: 1.5, Hires steps: 10, Hires upscaler: R-ESRGAN 4x+
Nastavení
Sampler
DPM++ 2M Karras
Kroky
30
Guidance
7
Seed
2858074253
Velikost
1024x1536
Clip skip
2
Prompt
<lora:Sy3:1> close up, (American Robin) in the Sy3 style, dripping
Negativní prompt
easynegative, human
Nastavení
Sampler
DPM++ SDE Karras
Kroky
14
Guidance
5.5
Seed
1779512272
Velikost
512x768
Clip skip
2
Prompt
<lora:Sy3:1> close up portrait, darth vader
Negativní prompt
easynegative
AI modely pro generování obrázků, videa a textu
bubble drip je LoRA pro rodinu Stable Diffusion 1.5 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 1.5, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Procházet podle rodiny modelů
Procházet všechny modely