Detalhes
Recomendado
Dark Kawaii - drkkaw-V2
V1
Dark Kawaii - drkkaw

Dark Kawaii - drkkaw

55
3
57
#Estilo

I would like to say thank you so much to MetroCat for helping me out with V2 and giving me some pointers on making it better I think my future Loras will come out way better because of it.

Dark Kawaii - drkkaw

I know its a long description if you don't like it don't read it. XD!

Prompt Used weights varied on tests.

Science Fiction, couch, <lora:drkkaw_epoch_10:0.8>,

I forgot to take out the negative prompt with the weights test but took the negative prompt out for the rest of the tests.

Negative prompt: JuggernautNegative

https://civitai.com/models/81563/juggernaut-negative-embedding?modelVersionId=86553

Sampler, Scheduler, Seed, and CFG are not important but I thought I would list them just incase you are curious.

Sampler: DPM++ 2M SDE

Scheduler: Karras

Seed: 586712160

CFG: 5

WEIGHTS!

Weights In this one came out tricky maybe you would say it's undertrained but I still think it came out good just need to raise weights instead of lowering I find 0.7 to 1.1 looks best but eye of the beholder and all that.

MODELS!

I find it is very picky with the models it works with which sucks because I love the PixelAhuskay model and I don't think it works well with it

Models tested "weights 0.7-1.1"

animeArtDiffusionXL_alpha2.safetensors [87f2e27ed8]

https://civitai.com/models/117259?modelVersionId=127055

realmixXL_v15.safetensors [ebf42d1fae]

https://civitai.com/models/124419?modelVersionId=136753

pixelAhuskay_v20.safetensors [1ef4aab75b]

https://civitai.com/models/537844/pixel-ahuskay

dreamshaperXL10_alpha2Xl10.safetensors [0f1b80cfe8]

https://civitai.com/models/112902?modelVersionId=126688

juggernautXL_version6Rundiffusion.safetensors [1fe6c7ec54]

https://civitai.com/models/133005?modelVersionId=198530

Trigger words?!?

The test above were used with the prompt

Science Fiction, couch, - then the lora and weight adjustments

this image shows with out the word Science Fiction.

Tags!

in automatic 1111 if you click on the lora tab.

Find the lora and click on the hammer and wrench.

Scroll down and you will find tabs.

Tags for your copy paste ease

robot, mecha, science fiction, glowing, no humans, realistic, non-humanoid, cable, standing, solo, one-eyed, radio antenna, spikes, weapon, antennae, lights, size difference, glowing eyes, gears, pink eyes, machinery, smoke, helmet, steampunk,

You can see how finding the tag words and testing them can change the image dramatically.

Prompt Problems?!?

Nice but lets say I was looking for more of a boy in the picture.

Amazing painting, boy, 10k ultra resolution, Science Fiction, weapon, <lora:drkkaw_epoch_10:0.8>

Steps: 35, Sampler: DPM++ 2M SDE, Schedule type: Karras, CFG scale: 5, Seed: 3187266996, Size: 1024x1224, Model hash: 53bb4fdc63, Model: animeArtDiffusionXL_alpha3, Lora hashes: "drkkaw_epoch_10: 98f8993d5274", Downcast alphas_cumprod: True, Version: v1.9.4

I put tag words I found in the instructions above in the negative prompt.

Amazing painting, boy, 10k ultra resolution, Science Fiction, weapon, <lora:drkkaw_epoch_10:0.8>

Negative prompt: robot, mecha, realistic, cable, one-eyed, radio antenna, spikes, antennae, lights, size difference, glowing eyes, gears, pink eyes, machinery, smoke, helmet, steampunk,

Steps: 35, Sampler: DPM++ 2M SDE, Schedule type: Karras, CFG scale: 5, Seed: 3187266996, Size: 1024x1224, Model hash: 53bb4fdc63, Model: animeArtDiffusionXL_alpha3, Lora hashes: "drkkaw_epoch_10: 98f8993d5274", Downcast alphas_cumprod: True, Version: v1.9.4

But lets say I wanted something a little more like a boy?!? leave the negative tags and lower the lora weight.

Amazing painting, boy, 10k ultra resolution, Science Fiction, weapon, <lora:drkkaw_epoch_10:0.6>

Negative prompt: robot, mecha, realistic, cable, one-eyed, radio antenna, spikes, antennae, lights, size difference, glowing eyes, gears, pink eyes, machinery, smoke, helmet, steampunk,

Steps: 35, Sampler: DPM++ 2M SDE, Schedule type: Karras, CFG scale: 5, Seed: 3187266996, Size: 1024x1224, Model hash: 53bb4fdc63, Model: animeArtDiffusionXL_alpha3, Lora hashes: "drkkaw_epoch_10: 98f8993d5274", Downcast alphas_cumprod: True, Version: v1.9.4

A friend gave me some pointers on ways that might make it better so I'm a try those and maybe have a newer version out by thee end of this weekend.

I talk a bit about it here I don't edit it so it's not safe to listen to at work or around family church wont like it that's for sure.

Ver tradução

Classificação e Avaliação

-- /5
0 classificação(ções)

Sem classificações ou avaliações suficientes

no-data
Sem dados
avatar
Conversar com o modelo
Anúncio
2024-07-11
Publicar Modelo
2024-07-14
Atualizar info do modelo
Detalhes do modelo
Tipo
LORA
Tempo de Publicação
2024-07-14
Modelo básico
SDXL 1.0
Palavra de ativação
drkkaw
kawaii
science fiction
robot
mecha
Copiar
Introdução à Versão

I would like to say thank you to MetroCat for giving me some pointers on making it a little better.

Weights are a little better in this one. Have fun and all that. I put drkkaw as a trigger word but didn't see it ad much when generating maybe you will ahve more luck though.

Escopo da licença
Fonte: civitai

1. Os direitos dos modelos repostados pertencem aos criadores originais.

2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar

Escopo da licença de criação
Transmissão ao vivo
Fusão
Permitir download
Licença comercial
Imagens geradas podem ser vendidas ou usadas para fins comerciais
Permitir revenda de modelos ou sua venda após a combinação
QR Code
Baixar App SeaArt
Continue sua jornada de criação com IA no celular