<h1 id="heading-77">Read Description</h1>Important: Having multiple models uploaded here on civitai has made it difficult for me to respond to each and every comment. One of the ways I plan on addressing this is via the creation of a pdf guide for each and every model (think of it as the models documentation). This will take a while though. So in the meantime, if you have any questions or feedback -<a target="_blank" rel="ugc" href="https://discord.com/channels/1010980909568245801/1073440375336882186">visit my thread of the Unstable Diffusion Discord</a><h3 id="heading-80">Like photorealism? Try my new fine-tune '<a target="_blank" rel="ugc" href="https://civarchive.com/models/109923/lomostyle">Lomostyle</a>'</h3><h3 id="heading-78">VAE Required</h3>Download VAE - <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main">https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main</a>|──sd|____|──stable-diffusion-webui|____|____|──models|____|____|____|──VAE|____|____|____|____|──&lt;Put your VAE file here&gt;<img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/74b86d4e-571e-4c67-93bd-658ed080a200/width=525/74b86d4e-571e-4c67-93bd-658ed080a200.jpeg" />Cine Diffusion - Fine tuned on cinematic stills and 35mm film.Note: Description is limited atm. Full PDF documentation is in the works.Have you heard of the high elves? If you're attempting to generate an image of a elf and aren't seeing pointy ears:<ul><li>Set your CFG to 7+</li><li>Make sure <code>elf</code> is closer towards the beginning of the prompt.</li></ul>Warning - This model is a bit horny at times. I tried to alleviate this by fine tuning the text-encoder using the class <code>nsfw</code> and <code>sfw</code>. Although this solution is not perfect. More experimentation is needed. I've had most success with adding <code>sfw</code> or <code>nsfw</code> within the first 75 tokens of the prompt. Adding <code>sfw</code> or <code>nsfw</code> to the negative prompt can also help.<h3 id="heading-79">Settings</h3>Clipskip : 1ETA Noise Seed Delta : 31337CFG : 6 - 8Sampler recommendations :<ul><li>DPM++ SDE Karras, 18-40 steps</li><li>Euler a, 20-32 steps</li><li>DPM++ 2M Karras, 30 - 70 steps</li><li>Heun, 20 -30 steps</li><li>Euler, 20 - 70 steps, Sigma Churn = 1</li></ul>These parameters are not strictly required, experiment around with other samplers and parameter values. You might find something that works better for you.Textual Inversion (Negative) used in sample images :<ul><li>Bad_prompts_version2 - <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><ul><li>Install location - <code>stable-diffusion-webui -&gt; embeddings -&gt; &lt;place .pt embedding here&gt;</code></li></ul></li></ul><h3 id="heading-80">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>Project AIO - <a target="_blank" rel="ugc" href="https://civarchive.com/models/18428/project-aio">https://civarchive.com/models/18428/project-aio</a></li><li>Eris - <a target="_blank" rel="ugc" href="https://civarchive.com/models/21952/eris">https://civarchive.com/models/21952/eris</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>

Cine Diffusion

Cine_Diffusion_v3Baseline model consists of :<ul><li>base_2 (trained for anatomy)</li><li>HDR1 (trained model for lighting/texture)</li><li>Cine_Diffusion_v1 (First attempt at this model that was based on SD 1.5)</li><li>Movie Diffusion - <a target="_blank" rel="ugc" href="https://civitai.com/models/8067/movie-diffusion-v12">https://civitai.com/models/8067/movie-diffusion-v12</a></li></ul>Training Data :Most of the cinematic film stills were obtained via <a target="_blank" rel="ugc" href="https://film-grab.com/">https://film-grab.com/</a>35mm stills were largely obtained via <a target="_blank" rel="ugc" href="https://www.lomography.com/films">https://www.lomography.com/films</a>Extra training:Text-encoder-only training for <code>nsfw</code> and <code>sfw</code> triggers. More info + training logs and sample data will be available once the documentation is uploaded.

Files with SHA256: 1c43e88a5e480ccaa1dbf0251ab6ab2440448ef9c447d3f99acf3937026a41c8