Joined January 2023
302 Photos and videos
Pinned Tweet
🚀Stable Diffusion 3.5を紹介します このオープンリリースには、サイズに対して非常にカスタマイズ性の高い複数のバリエーションが含まれており、一般のハードウェアで動作します。 Stable Diffusion 3.5 LargeおよびStable Diffusion 3.5 Large Turboは、現在Hugging Faceからダウンロードでき、推論用コードはGitHubで入手可能です。 詳しくはこちらをご覧ください。 ja.stability.ai/blog/introdu…
1
82
216
55,219
Stability AI Japan retweeted
29 Oct 2024
Stable Diffusion 3.5 Medium from @StabilityAI was just released! It's a 2.6B model that runs on a consumer GPU. Try it now in a ComfyUI instance near you!
10
29
253
49,551
Stability AI Japan retweeted
29 Oct 2024
Stable Diffusion 3.5 from @StabilityAI is now LIVE on Civitai! Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Generate with SD 3.5 Live on Civitai here👇🏽 civitai.com/models/878387?mo… All images used to create this video were generated with SD 3.5 by our community 🫶🏽
7
17
80
31,255
Stability AI Japan retweeted
Day ☝️!
29 Oct 2024
Stable Diffusion 3.5 Medium from @StabilityAI was just released! It's a 2.6B model that runs on a consumer GPU. Try it now in a ComfyUI instance near you!
1
8
80
23,650
Stability AI Japan retweeted
29 Oct 2024
Introducing Stable Diffusion 3.5 Medium - an attempt to, again, fit the world into a portable size model. It's more than just a smaller version; many thoughts have gone into this challenging task to make it "unique." Please try it, and tell me what you think.
Replying to @StabilityAI
This model delivers best-in-class image generation for its size, with advanced multi-resolution capabilities. It surpasses other medium-sized models with its prompt adherence and image quality, making it a top choice for efficient, high-quality performance. You can download the weights on @HuggingFace and inference code on @GitHub now. Learn more on our blog here: stability.ai/news/introducin… (3/3)
1
3
22
11,749
Stability AI Japan retweeted
The Stable Diffusion 3.5 (SD 3.5) model family is now on Fireworks! SD 3.5 reaches new heights in versatility, customizability and prompt following. Use the models with speed, cost-efficiency and customizability on Fireworks today.
1
11
22
17,763
🚀Stable Diffusion 3.5 Medium が登場しました! このオープンモデルは、25億のパラメータを持ち、消費者向けハードウェア上で「箱から出してすぐに」動作するように設計されています。 ブログにMediumの内容を追加しています。ぜひご覧ください。 ja.stability.ai/blog/introdu…
2
44
154
20,458
Stability AI Japan retweeted
LoRAs are weaving their way into SD3.5 already 🧶
progressing towards my SD3.5-large Yarn art LoRA 🧶 definitely an improvement on SD3, still figuring out what params work best but potential is definitely there i'd say ✨
1
6
74
19,662
Stability AI Japan retweeted
🚀Stable Diffusion 3.5を紹介します このオープンリリースには、サイズに対して非常にカスタマイズ性の高い複数のバリエーションが含まれており、一般のハードウェアで動作します。 Stable Diffusion 3.5 LargeおよびStable Diffusion 3.5 Large Turboは、現在Hugging Faceからダウンロードでき、推論用コードはGitHubで入手可能です。 詳しくはこちらをご覧ください。 ja.stability.ai/blog/introdu…
1
82
216
55,219
Stability AI Japan retweeted
The beauty of open models 🫶 Happy training!
Was fortunate enough to get to test this early (thank you @StabilityAI)! Huge step for open source models. We are all very lucky to be able to say that. Give it a try--I'm still learning, but find with this one, the more descriptive you are, the better🌸🥳 Next step: training!
5
9
88
22,007
Stability AI Japan retweeted
Did someone say ControlNets and IPAdapters are coming soon? 👀
22 Oct 2024
GM Stable Difusion 3.5 Large! I had the chance to play with the newly released model over the weekend. Here are a few of the results. Overall the model is a major improvement from the SD3 model released earlier this year. Below you will find some of the RAW outputs. 1/6 🧵👇
6
15
108
38,728
Stability AI Japan retweeted
ICYMI we released Stable Diffusion 3.5 today! These models are free for both commercial and non-commercial use under the permissive Stability AI Community License. We wanted to take a moment to highlight the key components of the license. You can learn more here: stability.ai/community-licen…
3
18
112
14,754
Stability AI Japan retweeted
Any 👏 Style 👏 Imaginable 👏
22 Oct 2024
#SD35L Is out! Unleash the styles! huggingface.co/stabilityai/s…
1
7
65
18,211
Stability AI Japan retweeted
Introducing Stable Diffusion 3.5, @StabilityAI’s most powerful models yet.  This open release includes multiple variants that are highly customizable for their size, run on consumer hardware, and are free for both commercial and non-commercial use under the permissive Stability AI Community License.  You can download Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo from Hugging Face and the inference code on GitHub now. Stable Diffusion 3.5 Medium will be released on October 29th.

Learn more here: stability.ai/news/introducin…

6
2
31
4,506
Stability AI Japan retweeted
22 Oct 2024
本日、Stable Diffusion 3.5 Large、及び Large-Turboがリリースされました。HuggingFace Spaceにて、実際に画像生成をお試しいただくことが可能です。 Large huggingface.co/spaces/stabil… Large-Turbo huggingface.co/spaces/stabil… 詳細なリリース内容は、以下をご覧ください。 ja.stability.ai/blog/introdu…
28
66
19,399
10月26日より、宮崎県の都城市立美術館で、特別展「わたしたちのグッドデザイン」展が開催されます。 SDXLは昨年、グッドデザイン賞ベスト100に選ばれました。 お近くにお住まいの方、ご旅行などで行かれる予定のある方はぜひ。 mcma-art.com/2024/
3
12
4,178
Stability AI Japan retweeted
Quest3単体で現実のオブジェクトをバーチャルの世界で複製できるようになった Echoes of Reality Take #3: Capturing Real-World Objects and Replicating Them in Quest 3’s Mixed Reality. Now achieved with #Quest3 alone.
29
197
884
96,768
Stability AI Japan retweeted
There’s a new update on Stable Assistant! 🔄 Replace Background: Effortlessly swap out the background of an image with precision, while keeping the main subject intact. Whether you want to enhance photos, create new environments, or adjust the mood of an image, Replace Background allows you to seamlessly transform your visuals without losing focus on the primary subject. Perfect for enhancing portraits, product photos, or creating unique compositions. 🔗 Get started with a 3-day free trial: stability.ai/stable-assistan…
13
20
128
19,967