#Books picks of the day:
➡️ @gutenberg_org (main) & @gutenberg_new (bot posting latest additions) - Huge digital library, distributing public domain books online
➡️ @bookwyrm - Fediverse alternative to Goodreads, track books, write reviews, discover readers etc
➡️ @internetarchive - Massive online archive of printed & other media
➡️ @DProofreaders - Volunteer project turning public domain books into eBooks
➡️ @inventaire - Free open platform for cataloguing physical book collections
1/10
RT @osanseviero
💫StarCoder: May the Source be with You!
🔥15B LLM with 8k context
🥳Trained on permissively-licensed code
💻Acts as tech assistant
🤯80+ programming languages
🚀Open source and data
💫Online demos
🧑💻VSCode plugin
🪅1 trillion tokens
Follow this amazing experience! 🧵
RT @SmokeAwayyy
❗Leaked Internal Google Document Claims Open Source AI Will Outcompete Google and OpenAI
https://www.semianalysis.com/p/google-we-have-no-moat-and-neither
RT @gabriel_ilharco
Today we are releasing a CLIP ViT-L/14 model with 79.2% zero-shot accuracy on ImageNet.
Our model outperforms OpenAI's CLIP by a large margin, and outperforms even bigger models (ViT-g/14) trained on LAION-2B
Check it out at https://huggingface.co/laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K!
RT @_akhaliq
DreamPaint: Few-Shot Inpainting of E-Commerce Items for Virtual Try-On without 3D Modeling
We introduce DreamPaint, a framework to intelligently inpaint any e-commerce product on any user-provided context image. The context image can be, for example, the user's own image for virtual try-on of clothes from the e-commerce catalog on themselves, the user's room image for virtual try-on of a piece of furniture from the e-commerce catalog in their room, etc. As opposed to previous augmented-reality (AR)-based virtual try-on methods, DreamPaint does not use, nor does it require, 3D modeling of neither the e-commerce product nor the user context. Instead, it directly uses 2D images of the product as available in product catalog database, and a 2D picture of the context, for example taken from the user's phone camera. The method relies on few-shot fine tuning a pre-trained diffusion model with the masked latents (e.g., Masked DreamBooth) of the catalog images per item, whose weights are then loaded on a pre-trained inpainting module that is capable of preserving the characteristics of the context image. DreamPaint allows to preserve both the product image and the context (environment/user) image without requiring text guidance to describe the missing part (product/context). DreamPaint also allows to intelligently infer the best 3D angle of the product to place at the desired location on the user context, even if that angle was previously unseen in the product's reference 2D images. We compare our results against both text-guided and image-guided inpainting modules and show that DreamPaint yields superior performance in both subjective human study and quantitative metrics.
RT @amygoodchild
Looking to blend colors in your generative artwork? I've explored a few methods for crafting the ideal gradient.
Check out the comparisons
https://editor.p5js.org/amygoodchild/sketches/T2jm6DBz9
Press 'c' to cycle through different colour pairs, or add your own hex codes to the array.
RT @_akhaliq
Unlimiformer: Long-Range Transformers with Unlimited Length Input
demonstrate Unlimiformer’s efficacy on several long-document and multi-document summarization benchmarks, showing that it can summarize even 350k token-long inputs from the BookSum dataset, without any input… https://twitter.com/i/web/status/1653577349374304256
RT @Oranguerillatan
Tests with the latest #warpfusion are coming along nicely, numerous #ControlNet flavours mixed in.
Kudos to @devdef always for his incredible tool and generous support community on Discord 🦧🦍🙏
My GPU survived the warp-ocalypse!💥
#GenerativeAI #AIArtistCommunity #AIArtworks… https://twitter.com/i/web/status/1653493879956557834
“Tests with the latest #warpfusion are coming along nicely, numerous #ControlNet flavours mixed in. Kudos to @devdef always for his incredible tool and generous support community on Discord 🦧🦍🙏 My GPU survived the warp-ocalypse!💥 #GenerativeAI #AIArtistCommunity #AIArtworks…”
Trevor Flowers
FediFollows
