Modelpublic

Emanon14/NONAMEmix-Vpred_v3

sourceHugging Faceotherupdated 1y agoView on Hugging Face

3likes34downloads

Model Card

NONAMEmix-Vpred v3.0

NOTICE

—This is a v-prediction model.
—99% of this checkpoint is made with RouWei.

Showcase

Portrait (Width 832 Height 1216) <img src="./sample01.png" alt="sample_v3_1"> Landscape (Width 1344 Height 768) <img src="./sample02.png" alt="samplev32">

Model Description

—Model type: Diffusion-based text-to-image generative model
—Model prompt style: Booru-tags & natural language
—License: Fair AI Public License 1.0-SD

Merge Recipe

—RouWei 0.7 vpred
—RouWei 0.8 vpred
—(https://civitai.com/models/950531/rouwei)
—CyberRealistic XL
—(https://civitai.com/models/312530/cyberrealistic-xl)
—stable-diffusion-xl-base-1.0
—(https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
—SPO-SDXL4k-p10epLoRAwebui
—(https://civitai.com/models/510261/spo-sdxl4k-p10eplorawebui)
—My LoRA
—One is trained by 300 images AI-generated
—The other is Trained by 500 images AI-generated

Recommended settings

—Positive prompts:

masterpiece, best quality

—Negative prompts:

worst quality, low quality, watermark

—CFG: 3-5
—Sampling steps: 28
—Sampler: Euler a
—Supported Resolution:

1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536

Thanks

—First of all, to Minthy for RouWei. That has the best prompt following I know of!
—And, of course, thanks for the Animagine. Animagine was the first signpost that led me to use SDXL, and it continues to do so!