File size: 2,648 Bytes
ba75e81 |
1 2 3 4 5 6 7 |
{
"activation text": "",
"description": "If you like my work, drop a 5 review and hit the heart icon. it's free and keeps me motivatedAll my models are officially hosted and maintained by me on Tensor.art http://Tensor.art . use my Exclusive and public model for free on tensor.art http://tensor.artCommission open in Patreon https://www.patreon.com/hinokiart. https://www.patreon.com/goofyaiGet early access and Exclusive NSFW Lora in my Patreon https://www.patreon.com/hinokiart . https://www.patreon.com/GoofyAiSupport my work by joining any one of them and get early access to all my upcoming loras and other perks such as fan requests and Discord role.Join my Discord Server https://discord.gg/M8yAsU9ZhCcurrently, only v3 and v4 are available for civitai generation.v3 got the most users so cant stop it. and getting feedback from v4 generation.v2 got very few use compared to v3 so if you really want to use v2 just follow the TA link. they are official partner. OR just wait few days till civitai adds new checkpoint systemWIP: Realistic | v4 lightningV4 Update :Added trained LoraCleaned styleBaked in VAEExtra trained data of 15000 stepsBetter Lora support.V3 Update :onsite generation https://tensor.art/models/772139385270444718 https://tensor.art/models/772139385270444718added some style to itshould give better face and eyesbetter NSFW supportswide range of Lora supportV1 lightning :8-stepsDPM++ 2MV2 update:onsite generation https://tensor.art/models/754887012743423435 https://tensor.art/models/754887012743423435has less style influencecan work with wide range of lorasbetter anatomybetter colorV1 update:On site generation closed for v1 on civitai for limitation of civitai.try tensor.art http://tensor.art if you want to use the online generation for v1https://tensor.art/models/724940954567461228/Prefect-Pony-XL-v1.0 https://tensor.art/models/724940954567461228/Prefect-Pony-XL-v1.0If you like my work then drop a 5 review and hit the heart icon. it's free and keeps me motivatedSuggested settings:I had CLIP skip 2 on every imageI had ENSD: 31337 all of themAll of them had highres.fix or img2img at higher resolution.I don't use restore facesI use afterdetailer for face detailsTiled diffusion for img2img upscaling and sometimes Noise Inversion for some more extra details.4x-Ultrasharp upscalerNOTE: if you find any prompt of the preview images look familiar it's because I've taken them from other model review images, Credits to the original authors. Thanks for the benchmark.",
"sd version": "Other",
"modelId": 439889,
"sha256": "95DED7D68535DC493F088B698DE8E7FFB79FE2E80BB84D9D3B821D1AC4EB0AAA"
} |