Introduce OpenVoice V2 - a Text-to-Speech model that can clone any voice and speak in any language.

Developed by MyShell and MIT CSAIL researchers.

🌐 Imagine your voice going global in multiple languages.
🔊 OpenVoice V2 breaks the language barrier and redefines voice

Hello everyone, we have just released an open source base model Neta Art XL1.0; it's the best anime base model in the community so far.
Release notes: nieta-art.feishu.cn/wiki/PpwqwVDzj…
Civitai: civitai.com/models/410737
Free trial: neta.art

It's a great honor to partner with Andrew Ng DeepLearning.AI on this Mistral AI course. Super excited for the launch!

🔌 IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models 🔥 Jupyter Notebook + Replicate 🥳

Thanks to IP-Adapter Team ❤ ComfyUI Team ❤ Matteo Spinelli ❤ (ComfyUI_IPAdapter_plus) Henrik Forstén ❤ (ComfyUi_NNLatentUpscale)

🌐page:

🔌 IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models 🔥 Jupyter Notebook 🥳

Thanks to Hu Ye ❤ Jun Zhang ❤ Sibo Liu ❤ Xiao Han ❤ Wei Yang ❤

Thanks to Matteo Spinelli ❤ (ComfyUI_IPAdapter_plus) Henrik Forstén ❤ (ComfyUi_NNLatentUpscale)

🌐page:

VBench update: We support evaluating Image-to-Video (I2V) models at 𝗩𝗕𝗲𝗻𝗰𝗵-𝗜𝟮𝗩
🖼️ Image Suite: multi-scale, multi-aspect-ratio, comprehensive content variety
📏 Dimensions: video-image consistency, camera motion, video quality, etc.
👨‍💻 Code: github.com/Vchitect/VBench

IPAdapter advanced weighting (Instant Style) implemented for sd-webui-controlnet. You can now freely control weight of each block on an intuitive UI 🤗github.com/Mikubill/sd-we…

Made a Colab for Llama-3 8B! 15 trillion tokens! So Unsloth AI now supports it! Uses free T4 GPUs.

Doing benchmarking, but ~2x faster and uses 80% less memory than HF+FA2! Supports 4x longer context lengths than HF+FA2. & inference is natively 2x faster.

colab.research.google.com/drive/135ced7o…

What Mark learned from Caesar Augustus about peace, youth, and open source:

Run Llama 3 Locally with Open-WebUI

This video is NOT sped up. The model downloaded from ollama (llama3:instruct), running with Open WebUI (Formerly Ollama WebUI), on a Macbook Pro M1 Max 64G.

You can run it right now on your own machine (Windows, Linux, Mac) with 1 click.

🦙🦙🦙🔥! Start deploying Llama 3 on vLLM now: github.com/vllm-project/v…

🎨🖌️ Adding Conditional Control to Text-to-Image Diffusion Models 🌈 Colorize Line Art 🔥 Jupyter Notebook + Replicate 🥳

Thanks to style2paints ❤ Anyi Rao ❤ Maneesh Agrawala ❤

📄paper: arxiv.org/abs/2302.05543
🧬code: github.com/lllyasviel/Con…
🍊jupyter by modelslab.com:

Meta released Llama 3 on my birthday! 🎂 Best present ever, thanks Meta! 😀

👑 Open-Source Winning! 🥳

Thanks to AI at Meta Llama 3 Team ❤

We can test 🦙 Meta Llama 3 70B and 🦙 Meta Llama 3 8B with a 🔥 cool and free chat UI on Replicate 🥳

llama3.replicate.dev please try it 🐣

Introducing Meta Llama 3: the most capable openly available LLM to date.

Today we’re releasing 8B & 70B models that deliver on new capabilities such as improved reasoning and set a new state-of-the-art for models of their sizes.

Today's release includes the first two Llama 3

Llama 3's out. Try it here: llama3.replicate.dev

Don't have a #mocap studio but have camera? Getting realistic animations into #Fortnite has never been easier. The Meshcapade #UEFN editor plugin lets you capture any motion with any camera and get state-of-the-art monocular #mocap onto your characters. Try it for free.

🧙‍♀️We not only opensource the models, but also share you how we reach that!

🚀So now let's verify step-by-step to review the whole training method of WizardLM-2 together:

-------- 🧵 --------

👉Motivation First:
As the natural world's human-generated data becomes