Eris, the Greek goddess of strife and discord.This is my first pure 3D render/Cartoon model. When I started working on this model I had almost zero knowledge on writing prompts for 3d renders/CGI. As such, my main goal for this model was quickly realized - Make a model that accepts photorealistic prompts and returns beautiful 3D rendered outputs. Normal 3D render/CGI prompts also work with this model.<h1 id="heading-21">Important Settings</h1>The following settings assume you're using webui by Automatic1111<ul><li>USE CFG VALUES BELLOW 8*<ul><li>This model does not respond well to CFG values above 8. With some caveats that will be explained bellow.</li><li>Do not go over 6 CFG with Euler a unless,</li><li>You are using Hires Fix. I found that you can go as high as 10 CFG with hires. fix enabled. This applies to all samplers.</li><li>DPM++ SDE Karras starts to degrade around 7 CFG if using <code>clip skip = 1</code>, no hires fix. However, if you're using DPM++ SDE Karras with <code>clip skip = 2</code> the CFG values can go up to at least 10 CFG without significant (if any) degradation.</li><li>General Advice:<ul><li>Do Not exceed 6 CFG with Euler a, unless using hires fix.</li><li>Do Not exceed 7 CFG with DPM++ SDE Karras with clip skip set to 1, unless using hires fix.</li><li>You Can go up to at least 10 CFG with DPM++ SDE Karras with clip skip set to 2, without using hires fix.</li><li>I could not test all samplers. If you notice broken compositions or distortions; lower your CFG value and/or enable hires fix. My own personal settings for hires fix can be found bellow.</li></ul></li><li>Thanks to Duo V2 on the Unstable Diffusion discord for helping me get to the bottom of this issue.</li></ul></li><li>VAE: vae-ft-mse-840000-ema-pruned.safetensors<ul><li>link - <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors">https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors</a></li><li>This is already baked into the model but it never hurts to have VAE installed.</li><li>Under <code>Settings -&gt; Stable Diffusion -&gt; SD VAE -&gt;</code> select the VAE you installed via dropdown. Then, uncheck <code>Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pit next to them</code></li></ul></li><li>Clip skip : 2<ul><li>This varies. Most of the time <code>Clip skip = 2</code> works best with this model. In the event you're not getting the results you want. First, try <code>Clip skip = 1</code>.</li></ul></li><li>ETA Noise Seed Delta: 31337<ul><li>Found in - <code>Settings -&gt; Sampler parameters -&gt; Eta noise seed delta</code></li></ul></li><li>Sigma Noise: 1</li><li>Sigma Churn: 0 or 1<ul><li>Optional - When using Euler, Heun, DPM2 samplers try setting <code>Sigma Churn = 1</code></li><li>Found in - <code>Settings -&gt; Sampler parameters -&gt; sigma churn</code></li></ul></li><li>Optional Negative Textual Inversion (TI): bad_prompt_version2<ul><li>link - <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt">https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt</a></li><li>Install to - <code>stable-diffusion-webui -&gt; embeddings</code></li><li>In webui - Add <code>(bad_prompt_version2:0.8)</code> at the end of your negative prompt.</li></ul></li><li>Optional Recommended Samplers:<ul><li>DPM++ SDE Karras // 18-35 steps</li><li>Euler // 40 - 80 steps // Sigma Churn : 1</li><li>DPM++ 2M Karras // 40 - 70 steps</li><li>DPM++ 2S a Karras // 30 - 75 steps</li><li>Heun // 20 - 30 steps // Sigma Churn : 1</li><li>DPM2 // 30 - 75 steps // Sigma Churn : 1</li><li>These are just recommendations; feel free to experiment with different values and samplers.</li></ul></li><li>Optional Hires. Fix settings (these are my go-to parameters):<ul><li>Upscaler : R-ESRGAN 4x+</li><li>Denoising strength: 0.3 - 0.35</li><li>The rest of the settings are up to you. They don't really impact the quality of the output.</li><li>Note: Hires Steps, if you're using high steps for SD - You can choose a hires step value lower than your SD step value. This will increase the generation times.<ul><li>For example; Let's say you're using Euler sampler @ 60 steps. You can then set the Hires Steps to ~40. Apposed to the default which is 0. Hires Steps = 0 means it will follow the same step value as sampler (Euler in this case). Lower Hires Step values will reduce generation time.</li></ul></li></ul></li><li>Optional Face Restoration:<ul><li>I use CODEFORMER @ 0.8 strength. Whether or not you use face restoration is up to you.</li></ul></li><li>Optional Quick Settings:<ul><li>For easier access to some of the settings in webui, you can move some settings sliders/dropdowns to the main interface (beside model selection).</li><li>Quick settings location -<ul><li>Settings -&gt; User interface -&gt; Quicksettings list</li></ul></li><li>My Quick settings -<ul><li><code>sd_model_checkpoint, CLIP_stop_at_last_layers, s_churn</code></li><li>Where:<ul><li><code>CLIP_stop_at_last_layers</code> is Clip Skip</li><li><code>s_churn</code> is sigma churn</li></ul></li></ul></li></ul></li></ul>PDF documentation is in the works.<hr /><h3 id="heading-58">Check out my other models</h3>SDXL<ul><li>Boomer Art Model - <a target="_blank" rel="ugc" href="https://civarchive.com/models/163139/boomer-art-model-bam">https://civarchive.com/models/163139/boomer-art-model-bam</a></li><li>LomoXL -<a target="_blank" rel="ugc" href="https://civarchive.com/models/156743/lomoxl"> https://civarchive.com/models/156743/lomoxl</a></li></ul>SD1.5<ul><li>Doomer Boomer - <a target="_blank" rel="ugc" href="https://civarchive.com/models/118247?modelVersionId=128239">https://civarchive.com/models/118247?modelVersionId=128239</a></li></ul><ul><li>Lomostyle - <a target="_blank" rel="ugc" href="https://civarchive.com/models/109923/lomostyle">https://civarchive.com/models/109923/lomostyle</a></li></ul><ul><li>Based Model - <a target="_blank" rel="ugc" href="https://civarchive.com/models/83991?modelVersionId=89262">https://civarchive.com/models/83991?modelVersionId=89262</a></li></ul><ul><li>Electric Eden - <a target="_blank" rel="ugc" href="https://civarchive.com/models/64355/electric-eden">https://civarchive.com/models/64355/electric-eden</a></li><li>Cine Diffusion - <a target="_blank" rel="ugc" href="https://civarchive.com/models/50000/cine-diffusion">https://civarchive.com/models/50000/cine-diffusion</a></li></ul><ul><li>Project AIO - <a target="_blank" rel="ugc" href="https://civarchive.com/models/18428/project-aio">https://civarchive.com/models/18428/project-aio</a></li></ul><ul><li>WonderMix - <a target="_blank" rel="ugc" href="https://civarchive.com/models/15666/wondermix">https://civarchive.com/models/15666/wondermix</a></li></ul><ul><li>Refined - <a target="_blank" rel="ugc" href="https://civarchive.com/models/8392/refined">https://civarchive.com/models/8392/refined</a></li></ul><ul><li>Experience - <a target="_blank" rel="ugc" href="https://civarchive.com/models/5952/experience">https://civarchive.com/models/5952/experience</a></li><li>Elegance - <a target="_blank" rel="ugc" href="https://civarchive.com/models/5564/elegance">https://civarchive.com/models/5564/elegance</a></li></ul><ul><li>Clarity - <a target="_blank" rel="ugc" href="https://civarchive.com/models/5062/clarity">https://civarchive.com/models/5062/clarity</a></li><li>VisionGen - Realism Reborn -<a target="_blank" rel="ugc" href="https://civarchive.com/models/4834/visiongen-realism">https://civarchive.com/models/4834/visiongen-realism</a></li></ul>LoRA<ul><li>Pant Pull Down - <a target="_blank" rel="ugc" href="https://civarchive.com/models/11126/pant-pull-down-lora">https://civarchive.com/models/11126/pant-pull-down-lora</a></li></ul>Questions or Feedback?<a target="_blank" rel="ugc" href="https://discord.com/channels/1010980909568245801/1073440375336882186">Visit my thread on the Unstable Diffusion Discord Server</a>

Eris

Initial ReleaseWhat's included? [Original Name | What Civitai will rename them]<ul><li>Eris_v1.safetensors | eris_v1.safetensors</li><li>Eris_v1.ckpt | eris_v1c.ckpt</li><li>Eris_v1-fp16.safetensors | eris_v1(1).safetensors</li></ul>This model is mainly a trained model. Initial model used for training is made up of the following merge:<ul><li>Rev_Animated - <a target="_blank" rel="ugc" href="https://civitai.com/models/7371/rev-animated">https://civitai.com/models/7371/rev-animated</a></li><li>sxdplus - <a target="_blank" rel="ugc" href="https://huggingface.co/NerdAINerd/sxdplus/tree/main">https://huggingface.co/NerdAINerd/sxdplus/tree/main</a></li><li>ZombiMixV9 - <a target="_blank" rel="ugc" href="https://huggingface.co/zombihed/ZombiMix-v6/tree/main">https://huggingface.co/zombihed/ZombiMix-v6/tree/main</a></li><li>Unvail AI 3DKX v2 - <a target="_blank" rel="ugc" href="https://civitai.com/models/2504/handas-3dkx-11">https://civitai.com/models/2504/handas-3dkx-11</a></li><li>Training was resumed with Noise Offset enabled.</li></ul>

Files with SHA256: 210d0d5d5d87b1a3977486f941af4a981f37083c3a183702a51aa043897121a3