Please read <a rel="ugc" href="https://civarchive.com/articles/6221">SD3 Unbanned: Community Decision on Its Future at Civitai</a><hr /><h3 id="stable-diffusion-3-(sd3)-2b-&quot;medium&quot;-model-weights!-4ttqjnfv3">Stable Diffusion 3 (SD3) 2B "Medium" model weights!</h3>Please note; there are many files associated with SD3. They will all appear on this model card as the uploads are completed.<a target="_blank" rel="ugc" href="https://education.civitai.com/quickstart-guide-to-stable-diffusion-3/">ℹ️ Read the Quickstart Guide!</a>Check out our <a target="_blank" rel="ugc" href="https://education.civitai.com/stable-diffusion-3-pre-release-overview/">pre-release SD3 Overview</a> for some information about the model, and the <a target="_blank" rel="ugc" href="https://education.civitai.com/quickstart-guide-to-stable-diffusion-3/">SD3 Quickstart Guide</a> to help you get started generating!<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2e56b69f-e774-471c-81d9-0ed37edda1fe/width=525/2e56b69f-e774-471c-81d9-0ed37edda1fe.jpeg" />There are three .safetensors versions;<ul><li>sd3_medium.safetensors</li><li>sd3_medium_inc_clips.safetensors</li><li>sd3_medium_inc_clips_t5xxlfp8.safetensors</li></ul>Stable Diffusion 3 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.For more technical details, please refer to the <a target="_blank" rel="ugc" href="https://stability.ai/news/stable-diffusion-3-research-paper">Research paper</a>.Please note: this model is released under the Stability Non-Commercial Research Community License. For a Creator License or an Enterprise License visit <a target="_blank" rel="ugc" href="http://Stability.ai">Stability.ai</a> for commercial licensing details.<h3 id="model-description-upi53649d">Model Description</h3><ul><li>Developed by: Stability AI</li><li>Model type: MMDiT text-to-image generative model</li><li>Model Description: This is a model that can be used to generate images based on text prompts. It is a Multimodal Diffusion Transformer (<a target="_blank" rel="ugc" href="https://arxiv.org/abs/2403.03206">https://arxiv.org/abs/2403.03206</a>) that uses three fixed, pretrained text encoders (<a target="_blank" rel="ugc" href="https://github.com/mlfoundations/open_clip">OpenCLIP-ViT/G</a>, <a target="_blank" rel="ugc" href="https://github.com/openai/CLIP/tree/main">CLIP-ViT/L</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/google/t5-v1_1-xxl">T5-xxl</a>)</li></ul><h3 id="license-i7u0cft7x">License</h3><ul><li>Non-commercial Use: Stable Diffusion 3 Medium is released under the <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/LICENSE.md">Stability AI Non-Commercial Research Community License</a>. The model is free to use for non-commercial purposes such as academic research.</li><li>Commercial Use: This model is not available for commercial use without a separate commercial license from Stability. We encourage professional artists, designers, and creators to use our Creator License. Please visit <a target="_blank" rel="ugc" href="https://stability.ai/license">https://stability.ai/license</a> to learn more.</li></ul>The original Huggingface Repository for SD3 can be found <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium">here</a>.

Stable Diffusion 3 (SD3)

stableDiffusion3SD3_comfyuiWorkflows_trainingData.zip

ComfyUI Workflows

SD3 Medium Incl Clip FP16

Text Encoder - T5XXLFP16

Text Encoder - T5 e4m3fn

SD3 Medium Incl T5XXL

Text Encoder - Clip G

Text Encoder - Clip L

SD3 Medium Incl. Clips

Demo Prompts

SD3 Medium

Files with SHA256: 89cab9df5c47f0bb15ecad045f059108deec4118b4d71f7c1bf7a02ab299ed8b