First and foremost - this model was uploaded without a Hyper merge by: <a target="_blank" rel="ugc" href="https://civarchive.com/user/jjambong000">jjambong000</a>Link to the original model:<a target="_blank" rel="ugc" href="https://civarchive.com/models/244724"> VixenMix v1.0</a>I have just merged the Hyper SD 1.5 (8 Steps) LoRA into it, with a specific ratio. The results were too nice to not upload the model, especially at just 8 steps (excluding the hires/upscale). This was mainly made for a <a target="_blank" rel="ugc" href="https://civarchive.com/bounties/4189/vixen-model-lcm">bounty</a> submission, requested by <a target="_blank" rel="ugc" href="https://civarchive.com/user/marcus199911">marcus199911.</a>VAE is baked in.<h2 id="note-the-following-gen-parameters-and-use-them-for-the-best-results:-g25cjisds">Note the following gen parameters and use them for the best results:</h2><ul><li>Sampler: DPM++ SDE (recommended)</li><li>Scheduler: sgm_uniform (IMPORTANT)</li><li>Steps: 8 (recommended)</li><li>CFG: 1.5 - 2</li><li>Hires fix or UltimateSDUpscale: Denoise at 0.28, 4x-UltraSharp, dpm++ sde, sgm_uniform at 1.7x.</li></ul>If you want to support more models like this, or you just like what you see: <a target="_blank" rel="ugc" href="https://ko-fi.com/nottheninja">ko-fi (｡♥‿♥｡)</a>Also, I don't plan on charging buzz for my LoRAs. So, I'd really appreciate if by any chance you could tip the model.

VixenMix - Hyperified (8 Steps SD 1.5 Hyper LoRA Merge)

vixenmixHyperified8StepsSD_v10.safetensors

v1.0

First and foremost - this model was uploaded without a Hyper merge by: <a href="https://civitai.com/user/jjambong000" rel="ugc noopener noreferrer nofollow" target="_blank">jjambong000</a>Link to the original model:<a href="https://civitai.com/models/244724" rel="ugc noopener noreferrer nofollow" target="_blank"> VixenMix v1.0</a>I have just merged the Hyper SD 1.5 (8 Steps) LoRA into it, with a specific ratio. The results were too nice to not upload the model, especially at just 8 steps (excluding the hires/upscale). This was mainly made for a <a href="https://civitai.com/bounties/4189/vixen-model-lcm" rel="ugc noopener noreferrer nofollow" target="_blank">bounty</a> submission, requested by <a href="https://civitai.com/user/marcus199911" rel="ugc noopener noreferrer nofollow" target="_blank">marcus199911.</a>VAE is baked in.<h2 id="note-the-following-gen-parameters-and-use-them-for-the-best-results:-g25cjisds">Note the following gen parameters and use them for the best results:</h2><ul><li>Sampler: DPM++ SDE (recommended)</li><li>Scheduler: sgm_uniform (IMPORTANT)</li><li>Steps: 8 (recommended)</li><li>CFG: 1.5 - 2</li><li>Hires fix or UltimateSDUpscale: Denoise at 0.28, 4x-UltraSharp, dpm++ sde, sgm_uniform at 1.7x.</li></ul>If you want to support more models like this, or you just like what you see: <a href="https://ko-fi.com/nottheninja" rel="ugc noopener noreferrer nofollow" target="_blank">ko-fi (｡♥‿♥｡)</a>Also, I don't plan on charging buzz for my LoRAs. So, I'd really appreciate if by any chance you could tip the model.

Files with SHA256: 719fc1201a7a76eb569b16ef3f76d08b87c14d30e2b7651d87c3c75478fa7de5