Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
Sy3.safetensors
72 MB · SafeTensor
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<bubble-drip>
À propos de ce modèle
STABLE DIFFUSION 1.5 · LoRA
Créé par
LDWorksDavid
sur 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
Notes du créateur
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.
Mots déclencheurs
Sy3
8,395 téléchargements · 1,597 j'aime sur Civitai
SHA256
C9F643A52CFEED29E0EFA6699AF5756B3B01571287741FDED79D83828AB63401
ID de modèle ModelTrends.ai
#8779
Signaler le contenu
Rendus d'exemple
Prompts et réglages partagés par les personnes qui ont réalisé ces rendus sur Civitai. Choisissez un rendu pour voir comment il a été fait.
Réglages
Sampler
DPM++ SDE Karras
Étapes
14
Guidance
7.5
Seed
2060676230
Taille
512x768
Clip skip
2
Prompt
<lora:Sy3:0.7> saturn in the style of sy3
Prompt négatif
easynegative
Réglages
Sampler
Euler a
Étapes
20
Guidance
7
Seed
3970782506
Taille
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,
Prompt négatif
(worst quality, low quality), bad_pictures, negative_hand-neg,
Réglages
Sampler
DPM++ SDE Karras
Étapes
14
Guidance
7
Seed
2258170680
Taille
512x512
Clip skip
2
Prompt
<lora:Sy3:1> a house
Prompt négatif
easynegative
Réglages
Sampler
DPM++ SDE Karras
Étapes
14
Guidance
5.5
Seed
4032918374
Taille
512x768
Clip skip
2
Prompt
<lora:Sy3:1> portrait, male, wizard, short red hair, sitting
Prompt négatif
easynegative
Réglages
Sampler
DPM++ 2M Karras
Étapes
20
Guidance
7
Seed
3767393822
Taille
1024x1536
Clip skip
2
Prompt
Superman Portrait , ((blue)) background ,Sy3,
Prompt négatif
16-token-negative-deliberate-neg, easynegative , By bad artist -neg
Réglages
Sampler
DPM++ 2S a Karras
Étapes
30
Guidance
7
Seed
2640592821
Taille
512x768
Prompt
clown, fantasy creature, Sy3, <lora:Sy3:.9> Best quality, masterpiece, ultra high res, absurdres,
Prompt négatif
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+
Réglages
Sampler
DPM++ 2M Karras
Étapes
30
Guidance
7
Seed
2858074253
Taille
1024x1536
Clip skip
2
Prompt
<lora:Sy3:1> close up, (American Robin) in the Sy3 style, dripping
Prompt négatif
easynegative, human
Réglages
Sampler
DPM++ SDE Karras
Étapes
14
Guidance
5.5
Seed
1779512272
Taille
512x768
Clip skip
2
Prompt
<lora:Sy3:1> close up portrait, darth vader
Prompt négatif
easynegative
Modèles d'IA pour générer image, vidéo et texte
bubble drip est un LoRA pour la famille Stable Diffusion 1.5, référencé sur ModelTrends.ai, un catalogue en lecture seule de modèles d'IA open source pour l'image, la vidéo et le texte. Comparez-le aux autres modèles Stable Diffusion 1.5, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Voir tous les modèles