<h2 id="heading-4">Updated v1.1 Pony Version</h2><h3 id="heading-19">update the variety for the Pony version model, which works better if there is a pony_score, you can refer to the parameters here</h3><a target="_blank" rel="ugc" href="https://civarchive.com/articles/4248/what-is-score9-and-how-to-use-it-in-pony-diffusion">What is score_9 and how to use it in Pony Diffusion | Civitai</a><h1 id="heading-45">Sora Ani2.5D</h1>My model focuses on anime styles from backgrounds, effects, etc. Currently, I can’t create anime characters because I’m collecting data to continue training my model. However, I think you will like my model. Give it a try, and if you like it, please rate me 5 stars.<h3 id="heading-49">Recommend</h3>Steps: 20,Sampler: DPM++ 3M SDE karas.CFG scale: 4-7,VAE: NoneHires steps: 5 Denoising Streng: 0.35Nprompt:worst quality, low quality, normal quality, painting by bad-artist______________________________________If your computer isn't powerful enough or you don't want to spend time setting it up, you can generate images directly from this model on the online platform that supports GPU<a target="_blank" rel="ugc" href="https://tensor.art/u/627089981680276847">(4) Creator profile SoraSleep | </a><a target="_blank" rel="ugc" href="http://Tensor.Art">Tensor.Art</a>______________________________________<h3 id="heading-238">Note:</h3>Don’t increase the weight of words too high, especially with words like “style of Artist”. My model will rely on the images of the base SDXL model.Supporting me: <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/sorasleep">SoraSleep - Buymeacoffee</a>Contact for working: <a target="_blank" rel="ugc" href="https://linktr.ee/sorasleepai">https://linktr.ee/sorasleepai</a>

Sora Ani2.5D | SDXL & Pony

soraAni25DSDXLPony_v10.safetensors

v1.0

v1.1Pony

Sora Ani2.5DMy model focuses on anime styles from backgrounds, effects, etc. Currently, I can’t create anime characters because I’m collecting data to continue training my model. However, I think you will like my model. Give it a try, and if you like it, please rate me 5 stars.RecommendSteps: 30-40,Sampler: DPM++ 3M SDE karas.CFG scale: 4-7,VAE: NoneHires steps: 15 Denoising Streng: 0.35Model training with size: 512x512Nprompt:worst quality, low quality, normal quality, painting by bad-artist______________________________________If your computer isn't powerful enough or you don't want to spend time setting it up, you can generate images directly from this model on the online platform that supports GPU<a href="https://tensor.art/u/627089981680276847" rel="noopener noreferrer nofollow">(4) Creator profile SoraSleep | </a><a href="http://Tensor.Art" rel="ugc noopener noreferrer nofollow" target="_blank">Tensor.Art</a>______________________________________Note:Don’t increase the weight of words too high, especially with words like “style of Artist”. My model will rely on the images of the base SDXL model.Supporting me: <a href="https://www.buymeacoffee.com/sorasleep" rel="ugc noopener noreferrer nofollow" target="_blank">SoraSleep - Buymeacoffee</a>Contact for working: <a href="https://linktr.ee/sorasleepai" rel="ugc noopener noreferrer nofollow" target="_blank">https://linktr.ee/sorasleepai</a>

Files with SHA256: c6a38ede7ccafff17bdb23f786617b592ab57e6c81439bbef74016fcb8a8f4e0