FASHN AI

428 posts

FASHN AI banner
FASHN AI

FASHN AI

@fashn_ai

The AI studio for fashion brands. Making premium imagery accessible for everyone. Founded by @ayaboch & @DanBochman

Katılım Haziran 2023
5 Takip Edilen2.8K Takipçiler
Sabitlenmiş Tweet
FASHN AI
FASHN AI@fashn_ai·
🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.
English
12
20
260
19K
FASHN AI retweetledi
Aya Bochman
Aya Bochman@ayaboch·
we’re hiring a customer success engineer at FASHN. *remote, Europe timezone preferred (founders based in Paris) last time I posted a role on X it worked incredibly well. we hired 2 amazing engineers, and since then we’ve more than doubled our revenue. now we’re ready to grow the team again. we’re looking for someone who genuinely cares about helping users succeed and can make sure that when people sign up to FASHN they feel supported, whether through clear docs, tutorials, videos, onboarding, or fast help from a real person when they get stuck. you’ll see the impact of your work almost immediately and very clearly: hundreds of people use the FASHN app every day, and thousands more use FASHN across the platform. referrals are more than welcome :) link to the full job description in the thread
English
6
9
31
3K
FASHN AI
FASHN AI@fashn_ai·
Introducing: 📂 Collections You can now organize your generated assets in the Gallery with Collections. Group images by project, season, style, or however you like, and rename or delete Collections at any time. Go create your first Collection in the FASHN app! 🏃‍♂️
FASHN AI tweet media
English
0
0
4
279
FASHN AI
FASHN AI@fashn_ai·
🚨 New in the FASHN App: Multi Image Uploader You can finally make that dress + bag + shoes combo 😎 Upload up to 3 product images to create perfectly curated try-ons and professional on-model photoshoots that capture every detail. Available now in the FASHN app
English
0
0
7
256
FASHN AI
FASHN AI@fashn_ai·
Today we’re launching FASHN Pets™ ・Swap your dog with any breed ・Create professional product-to-pet images ・Try on collars Available now on the FASHN app 🐶
FASHN AI tweet mediaFASHN AI tweet mediaFASHN AI tweet media
English
1
0
7
1.5K
FASHN AI
FASHN AI@fashn_ai·
We added 70+ in-house, ready-to-use realistic models. 👉 Select your product 👉 Choose a model 👉 Generate try-ons and edit poses for multiple angles No need to chase the perfect prompt. Just plug in and start creating beautiful product photos for your brand.
English
0
2
6
503
FASHN AI
FASHN AI@fashn_ai·
✨ We’ve redesigned the FASHN AI app with a new unified Studio. All tools in one workspace. Move between steps, continue anytime, and access your session history with ease. ⚡ Built for speed, clarity, and creative control. Tell us what you think.
FASHN AI tweet media
English
1
1
5
1.3K
FASHN AI retweetledi
Tom Mulder
Tom Mulder@darkseed·
Having some fun with my new personal stylist Reachy Mini. It calls a API on the NVIDIA DGX Spark, which runs an open model by FASHN called fashn-vton-1.5 while having a conversation with you. @pollenrobotics x @huggingface x @nvidia #NVIDIAGTC #reachymini #dgxspark Reachy Mini ✅ DGX Spark ✅ Clothing ✅ Shoes ❌ Thank you Aya Bochman & Fashn team, but please can you also put out a shoe model. I cannot go to #GTC2026 on my socks 🧦
English
0
3
11
1.1K
FASHN AI retweetledi
fahad
fahad@fahadshaikhx·
It’s been pretty fun building this so far Early build features include: - simple & basic user flow for signup - pre-curated outfit catalog - @fashn_ai integration: upload selfie → generate avatar → see an item on your avatar
fahad tweet media
English
2
2
4
1.3K
FASHN AI
FASHN AI@fashn_ai·
🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.
English
12
20
260
19K
FASHN AI
FASHN AI@fashn_ai·
@3anpei ありがとうございます! 共有していただき助かります。 ご質問があれば、いつでもお知らせください。
日本語
0
0
1
46
Machine Delusions
Machine Delusions@Machinedelusion·
Interesting! Pixel Space diffusion model for fashion try on
FASHN AI@fashn_ai

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

English
2
3
25
2.4K
FASHN AI
FASHN AI@fashn_ai·
@ResistAiArt Thank you! we're here if you have any questions :)
English
0
0
1
50
Resist • 抵抗
Resist • 抵抗@Resists_AiArt·
This is really cool 😅
FASHN AI@fashn_ai

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

English
1
0
5
246
ztoh
ztoh@ZtohAic·
我去，这都把小厂逼到不行了都
FASHN AI@fashn_ai

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

中文
1
0
5
202

Keşfet

@ayaboch @TejasKumar_ @YouTube @pollenrobotics @huggingface @nvidia @FawazShak @3anpei