# SoteDiffusion V2An anime finetune of Würstchen V3 / Stable Cascade.# Release Notes- This release is sponsored by <a target="_blank" rel="ugc" href="https://fal.ai/grants?rel=sote-diffusion">fal.ai/grants</a>- Trained on 12M text &amp; image paris including WD tags and natural language captions for a single epoch on 8xH100 80GB SXM5 GPUs.- Trained with Full FP32 and MAE Loss.# ComfyUIUse these arguments when starting ComfyUI: --fp16-vae --fp16-unetDownload the Stage C to unet folder: <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/703072?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp16">https://civarchive.com/api/download/models/703072?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp16</a>Download the Stage C Text Encoder to clip folder: <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/704783?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp16">https://civarchive.com/api/download/models/704783?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp16</a>Download the Stage B to unet folder: <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/704646?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp16">https://civarchive.com/api/download/models/704646?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp16</a>Download the Stage A to vae folder: <a target="_blank" rel="ugc" href="https://huggingface.co/madebyollin/stage-a-ft-hq/resolve/main/stage_a_ft_hq.safetensors">https://huggingface.co/madebyollin/stage-a-ft-hq/resolve/main/stage_a_ft_hq.safetensors</a>Download the workflow and load it: <a target="_blank" rel="ugc" href="https://huggingface.co/Disty0/sotediffusion-v2/resolve/main/comfyui_workflow.json?download=true">https://huggingface.co/Disty0/sotediffusion-v2/resolve/main/comfyui_workflow.json?download=true</a>Stage C sampler: DPMPP 2M or DPMPP 2M SDE with SGM Uniform schedulerStage C steps: 28Stage C CFG: 6.0Stage B sampler: LCM with Exponential schedulerStage B steps: 14Stage B CFG: 1.0## <a target="_blank" rel="ugc" href="http://SD.Next">SD.Next</a>URL: <a target="_blank" rel="ugc" href="https://github.com/vladmandic/automatic/">https://github.com/vladmandic/automatic/</a>Go to Models -&gt; Huggingface and type Disty0/sotediffusion-v2 into the model name and press download.Load Disty0/sotediffusion-v2 after the download process is complete.Prompt:```your prompt goes herevery aesthetic, best quality, newest,```(New lines act the same way as BREAK in <a target="_blank" rel="ugc" href="http://SD.Next">SD.Next</a>)Negative Prompt:```very displeasing, displeasing, worst quality, bad quality, low quality, realistic, monochrome, comic, sketch, oldest, early, artist name, signature, blurry, simple background, upside down,```Parameters:Sampler: DefaultSteps: 28Refiner Steps: 14CFG: 5.0 to 6.0Secondary CFG: 1.0 to 1.5Resolution: 1280x1280, 1024x1536, 1024x2048, 2048x1152Anything works as long as it's a multiply of 128.## LicenseSoteDiffusion models falls under [Fair AI Public License 1.0-SD](<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a>) license, which is compatible with Stable Diffusion models’ license. Key points:1. Modification Sharing: If you modify SoteDiffusion models, you must share both your changes and the original license.2. Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.3. Distribution Terms: Any distribution must be under this license or another with similar rules.4. Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.Notes: Anything not covered by Fair AI license is inherited from Stability AI Non-Commercial license.

SoteDiffusion V2

Trained with Full FP32 and MAE Loss.

Files with SHA256: 02139c3eaff76b043c59ec7485a93ebee23ee96d4e38ff2b9ca063e20808c2b1