Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10) header
Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10) profile picture
London
Joined October 2018
Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)Photo by Lewis - Lead Recruiter @ Canva Research (@LewisForsyth10)
Lewis - Lead Recruiter @ Canva Research retweeted
Just have a try on Canva Craft model with this prompt: “Generate a 4:3 promotional poster for the release of the Canva Craft model mentioned at this link: canva.com/newsroom/news/canv…”. Here are the images you’ll get: Please simply replace the URL with any links you have interest🥰
Introducing Canva Craft 🚀 Extraordinary image generation is now available to everyone, powered by our first frontier model built specifically for design. With Craft, Canva is now the world's second most advanced AI lab for image generation on @DesignArena's global leaderboard. See what it can do 👇
1
3
14
891
Lewis - Lead Recruiter @ Canva Research retweeted
Canva Craft, the first ever image model by @canva, takes the #4 spot on DesignArena's Image leaderboard. This makes Canva the #2 Image Lab after @OpenAI! Notably, it wins most often on photorealistic product and object shots, setting up studio-style lighting and detailed material textures on a single hero object. It also ranks #1 on the Portrait and Landscape subcategories. Congrats to the @canva team on the launch!
22
55
22
303
41,224
Lewis - Lead Recruiter @ Canva Research retweeted
We’re excited to launch #MagicLayers globally at Canva 🚀🚀🚀 This is currently the most advanced image-to-layer decomposition model in the world-purpose-built for design-native content. ⚡ 20–200× faster than Qwen-Image-Layer 🎨 Super strong on designs canva.com/newsroom/news/magi…
3
11
2
34
8,645
Lewis - Lead Recruiter @ Canva Research retweeted
Have you ever gotten tired of boring plain linear layers and wanted a more complex function? We find that attaching low rank nonlinear residual functions can significantly accelerate pretraining, with an identified variant, CosNet, consistently observing 20+% wallclock speedup!
16
46
5
261
43,135
Lewis - Lead Recruiter @ Canva Research retweeted
Leonardo is entering a new era. Take these symbols and make them yours in Leonardo. Comment “Symbols” to receive these icons and get 60,000 tokens to start creating (while free premium subscriptions remain available.) Tag us when you post for a chance to be featured on our feed.
866
151
30
823
4,407,985
Lewis - Lead Recruiter @ Canva Research retweeted
Blueprints by Leonardo Ready-made workflows. Endless creativity. Blueprints combine models, prompts, and settings into one streamlined flow. Soon, you'll be able to build your own Blueprints, share them with the community, and access them through the Leonardo API. Turn your favorite creative processes into repeatable systems that work the way you do. Blueprints will evolve with the community, inspired by your creations, ideas, and feedback. Together, we're building a future where creativity is limitless, repeatable, and uniquely yours. Try Blueprints for 75% off. Your shortcut to pro results.
37
31
8
192
928,080
Lewis - Lead Recruiter @ Canva Research retweeted
🎬 Motion Control has arrived! Take full control of your AI videos with 12 dynamic camera shots — from smooth Dolly moves to dramatic Cranes and VFX like Explosions and Disintegration. Perfect for adding cinematic flare, stock footage, product ads, or just experimenting with storytelling. ✨ How it works: 1️⃣ Head to the new Video creation tool 2️⃣ Enter your prompt 3️⃣ Pick your camera shot from the Motion Control panel 4️⃣ (Optional) Add a Style or inspiration image as a start frame 💡Want extra consistency? Train an Element, generate your key stills, and animate them for a fully guided scene. More features are coming soon — including End Frames 👀  So stay tuned, and let us know what you create! 🎥 Lights, camera... Motion! Try it now on the Video page 👉🏻 bit.ly/3E7mI6s
43
35
8
243
984,548
Getting some great results from Flow State already 🚀
✨ Meet Flow State – Leonardo's newest feature for unlocking boundless creativity. Flow State delivers a continuous stream of possibilities from just one prompt. Perfect for breaking through creative blocks & staying in the zone. What’s inside? 👇
1
85
Lewis - Lead Recruiter @ Canva Research retweeted
Content Reference hits the mark - check out the consistency from the original image to the new creation 🎯
8
11
1
75
4,586
Lewis - Lead Recruiter @ Canva Research retweeted
Check out this new NanoGPT training speed record 🚀 The @leonardoai team are thrilled to play a small part in it. Keep the records coming, @hi_tysam 🙌
New NanoGPT training speed record: 3.28 FineWeb val loss in 4.66 minutes Previous record: 5.03 minutes Changelog: - FlexAttention blocksize warmup - hyperparameter tweaks
2
3
20
3,923
Great work from the audio team here 🎵
Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt. Explore the model and start creating for free at: stableaudio.com Read the blogpost here: bit.ly/3xlwmP5 (1/3)
96
Lewis - Lead Recruiter @ Canva Research retweeted
We release Stable Code Instruct 3B today. A super fast & light model that helps you code in the most popular programming languages such as Python, Javascript or SQL. Awesome work by the language team at Stability! See video below & try it out here: huggingface.co/spaces/stabil…
Introducing Stable Code Instruct 3B, our new instruction tuned LLM based on Stable Code 3B. With natural language prompting, this model can handle a variety of tasks such as code generation, math and other software engineering related outputs. This model’s performance rivals models of similar or larger sizes, including Codellama 7B Instruct and DeepSeek-Coder Instruct 1.3B. The model is available now for commercial and non-commercial use with a Stability AI Membership. Learn more and read the research paper here: bit.ly/3TMQCll
3
22
144
33,236
We're hiring a HR Manager in the US. If you're interested in designing and building process from the ground up, preferably within a tech company, I'd love to speak! #hr #people #ai lnkd.in/gZCuy3Mf
1
52
Exciting times! This week we released StableLM 🎉🚀 The first of Stability AI's large language models, starting with 3B and 7B param models, with 15-65B to follow. Released under CC BY-SA license. RLHF-tuned models for research re…lnkd.in/g8enbD_D stablelm.co
1
1
1
95