modelos/Stable Diffusion 3 (SD3) - SD3 Medium

Stable Diffusion 3 (SD3) - SD3 Medium

7/19/2025

11:24:24 AM

Palavras-chave e Tags Relacionadas

base model,basemodel,checkpoint,image generation,mmdit text-to-image model,multimodal diffusion transformer,sd 3,sd3,sd3 medium,stable diffusion 3,stable diffusion 3 (sd3),theally

A chibi style cat running on hind legs while holding a large silver fish in its front paws, being chased by an angry fishmonger in a busy open-air market street.

A beautiful female with long dark hair in a white bikini holding a wooden sign that says 'Free the Melons' standing in a lush jungle with a sad expression.

A serene Azeroth night elf forest landscape featuring a sunlit river reflecting lush green trees, shadows, and highlights in HDR quality.

A semi transparent woman figure formed by glowing blue streaks and plumes of magic energy standing against a starry deep space background with volumetric lighting effects.

A volcano erupts by the ocean, with bright orange lava flowing down its rocky sides and thick black smoke rising into the blue sky.

A massive volcano erupting with bright lava and smoke towering over a large urban city under a clear blue sky with clouds

A radiant angelic being named Seraphina stands with large white celestial wings, wearing a flowing white gown glowing under divine light in a serene heavenly landscape.

Hyper realistic half-body portrait of a 20-year-old girl with long dark hair in a ponytail wearing an intricately detailed black lace dress, against a deep blue and purple mysterious background.

Movie poster featuring a mechanical human-tank cyborg girl with short blonde hair, mounted on a wide tank with big wheels on green grass under blue sky, titled 'I Can Go Everywhere Now'.

Portrait of an armored war turtle cyborg with blue and yellow mechanical armor in a detailed 3D render, inspired by renaissance brush paintings.

Portrait of a woman wearing glasses adorned with a crown of white flowers, bathed in ethereal light, surrealistic style with Japanese mythology influences

A hyper-realistic image of a serious man wearing a dark suit standing in a sunlit garden pathway framed by lush green and red flowering plants and architectural railings.

Dicas

Refer to the official research paper at https://stability.ai/news/stable-diffusion-3-research-paper for technical details.

Please note that Stable Diffusion 3 is released under a non-commercial license; for commercial use, acquire a Creator or Enterprise License at https://stability.ai/license.

Access the Quickstart Guide and pre-release overview to get started efficiently with SD3.

Destaques da Versão

The 2B Parameter "Medium" weights. Note: no Text Encoder included! Read the Quickstart Guide for more information!

Patrocinadores do Criador

Please read SD3 Unbanned: Community Decision on Its Future at Civitai

ℹ️ Read the Quickstart Guide!

Check out our pre-release SD3 Overview and the SD3 Quickstart Guide to begin generating images quickly and effectively.

Stable Diffusion 3 Image

Please read SD3 Unbanned: Community Decision on Its Future at Civitai

Stable Diffusion 3 (SD3) 2B "Medium" model weights!

Please note; there are many files associated with SD3. They will all appear on this model card as the uploads are completed.

ℹ️ Read the Quickstart Guide!

Check out our pre-release SD3 Overview for some information about the model, and the SD3 Quickstart Guide to help you get started generating!

There are three .safetensors versions;

sd3_medium.safetensors
sd3_medium_inc_clips.safetensors
sd3_medium_inc_clips_t5xxlfp8.safetensors

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 Research paper.

Please note: this model is released under the Stability Non-Commercial Research Community License. For a Creator License or an Enterprise License visit Stability.ai for commercial licensing details.

Model Description

Developed by: Stability AI
Model type: MMDiT text-to-image generative model
Model Description: This is a model that can be used to generate images based on text prompts. It is a Multimodal Diffusion Transformer (https://arxiv.org/abs/2403.03206) that uses three fixed, pretrained text encoders (OpenCLIP-ViT/G, CLIP-ViT/L and T5-xxl)

License

Non-commercial Use: Stable Diffusion 3 Medium is released under the Stability AI Non-Commercial Research Community License. The model is free to use for non-commercial purposes such as academic research.
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 https://stability.ai/license to learn more.

The original Huggingface Repository for SD3 can be found here.