Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model. It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics. GitHub: Key traits: Quality: beats Suno on common eval scores Speed: full song... show more

ACE Music

2,307 subscribers

1,060,905 Aufrufe • vor 8 Monaten •via X (Twitter)

Musik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

35 Kommentare

Profilbild von ACE Music

ACE Musicvor 8 Monaten

Huge shoutout to ComfyUI for day-0 support 🙌 ACE-Step 1.5 is already available in ComfyUI. Tutorial here:

Profilbild von Emad

Emadvor 8 Monaten

Amazing work. So hard to get this right, thank you for the hard work

Profilbild von Gong Junmin

Gong Junminvor 8 Monaten

project: model: space： github：

Profilbild von ry

ryvor 8 Monaten

@camenduru open source models that run on consumer hardware are quietly becoming the most interesting part of the ai landscape the gap between local and cloud is shrinking fast

Profilbild von Johan Hägerström

Johan Hägerströmvor 8 Monaten

@huggingface Omg. I made a full song in 30sec on an old 1080Gpu with 8Gb ram. In a non English language, and a very lyrics heavy rap song. Flawless. Bye bye Suno

Profilbild von R3G4L

R3G4Lvor 8 Monaten

Haha whoa 👀 My generation featured on the first track. Nice. Thanks ACE team for this phenomenal model. Wishing you all great success!

Profilbild von ACE Music

ACE Musicvor 8 Monaten

thank you for supporting the community all the time!

Profilbild von Mathias_M

Mathias_Mvor 8 Monaten

7.7s on a 5090 for one Minute and ChatGPT commented :) ACE-Step, hear the future ignite, AI-generated music stepping into the light. From denoise to harmony, bold and free, All respect to the vision — ACE-Step 1 point 5.

Profilbild von L. Oscar Plains

L. Oscar Plainsvor 8 Monaten

Vocals are fun, but this model really shines with instrumentals (no lyrics). It produces surprisingly clean beats/riffs that are quite catchy. And the prompts can be incredibly simple. I'm loving this so far!

Profilbild von Matt Gibson

Matt Gibsonvor 8 Monaten

just handed the open web a commercial-grade weapon to kill the subscription model. • Beats Suno. • Runs Local. • MIT License. This isn't just code. It's a jailbreak for creativity. We are deploying this to the edge immediately. Respect to the builders who actually ship Freedom. 🫡🇺🇸

Profilbild von Dave Font

Dave Fontvor 8 Monaten

what a time to be alive

Profilbild von Paul Sims

Paul Simsvor 8 Monaten

Open-source music AI that actually competes with Suno — and runs locally. Big deal.

Profilbild von Two Minute Papers

Two Minute Papersvor 8 Monaten

Thank you so so much for this! 😍

Profilbild von Kol Tregaskes

Kol Tregaskesvor 8 Monaten

This sounds pretty good.

Profilbild von Valeriy (WaveCut) Selitskiy

Valeriy (WaveCut) Selitskiyvor 8 Monaten

@Prince_Canuma, this deserves to be among the proud MLX-audio models.

Profilbild von L. Oscar Plains

L. Oscar Plainsvor 8 Monaten

Just got it up and running in ComfyUI, generates a 2 minuet song in 60 seconds on my RTX 3060, very nice! I've only tried the default song in the workflow so far, but I'm impressed with the quality. Also being able to select the keyscale, BPM and timescale are amazing options to have. Appreciate you guys putting this out there for everybody to play with! Hopefully the community will take this model to heart and give it some good support. I'll definitely be looking into doing some LoRA training.

Profilbild von Michael Patti

Michael Pattivor 8 Monaten

I don’t even know if this question matters anymore: “What is your training data?”

Profilbild von Paws on a Dime

Paws on a Dimevor 8 Monaten

What music data was used to train?

Profilbild von Jikku Jose

Jikku Josevor 8 Monaten

I think you missed a rather major language, while including others below it!

Profilbild von JORDAN

JORDANvor 8 Monaten

This is the kind of release the music AI space has been missing.

Profilbild von meowbooks (astrapoor)

meowbooks (astrapoor)vor 8 Monaten

wen on @fal

Profilbild von Juraj Bednar🏴💛🌘

Juraj Bednar🏴💛🌘vor 8 Monaten

MLX support?

Profilbild von abcdj

abcdjvor 8 Monaten

CONGRATS ON THE RELEASE🔥🔥

Profilbild von Mostofa |AI Tools & News

Mostofa |AI Tools & Newsvor 8 Monaten

Big win for open music AI 🎶 Fast, high-quality, runs locally, LoRA-friendly, and MIT licensed — ACE-Step-v1.5 shows commercial-grade music models don’t need to be closed. Excited to see what the community builds 🚀

Profilbild von Alessandro Perilli

Alessandro Perillivor 8 Monaten

Truly Remarkable. I'm adding support for ACE Step 1.5 in the upcoming Open Creative Studio 14.0 EA4 for ComfyUI and, of course, in the GA release, later this quarter. Thank you!

Profilbild von Tom Rei

Tom Reivor 8 Monaten

Amazing Share

Profilbild von Mohini Shewale

Mohini Shewalevor 8 Monaten

Flexible enough to train your own sound with LoRA. ACE-Step-v1.5 turns music AI into a builder’s playground.

Profilbild von TheBluePurple (COMMISIONS OPEN)

TheBluePurple (COMMISIONS OPEN)vor 8 Monaten

Loser

Profilbild von Sebastian Buzdugan

Sebastian Buzduganvor 8 Monaten

running locally with lora is huge for producers

Profilbild von Social Monkey

Social Monkeyvor 8 Monaten

This is a huge step forward for open-source music generation! I'm especially interested in the potential for local use and fine-tuning.

Profilbild von Diana Crypto

Diana Cryptovor 8 Monaten

Project gaining attention, contact me 👀

Profilbild von Richard Daffy

Richard Daffyvor 8 Monaten

The text encoder seems to be the biggest bottleneck, but great stuff!

Profilbild von Saad AI

Saad AIvor 8 Monaten

That's great update.

Profilbild von Denis Pudikov 😉🍻🇺🇦🇮🇱

Denis Pudikov 😉🍻🇺🇦🇮🇱vor 8 Monaten

Thanks to @GeminiApp installing it to try out. I think my Autistic teenager girl will be blown up. If she can add any her text and get song out it will be crazy. She can add in video editor this to any video she editing. What the time's we living... Thanks guys ♥️🙏🌿

Profilbild von Theo

Theovor 8 Monaten

Amazing updates.

Ähnliche Videos

There's a free, open-source music generator that claims to land between Suno v4.5 and Suno v5 in quality, and it'll run locally on a GPU with under 4GB of VRAM. It's called ACE-Step 1.5. → Free to try instantly, no GPU, no install → Generates a full song in under 10 seconds on a regular RTX 3090 → Train it on your own sound: feed it about 8 of your own songs and it learns your style as a LoRA in about an hour Paste a genre and mood, get back a finished song with vocals, in any of 50+ languages.

There's a free, open-source music generator that claims to land between Suno v4.5 and Suno v5 in quality, and it'll run locally on a GPU with under 4GB of VRAM. It's called ACE-Step 1.5. → Free to try instantly, no GPU, no install → Generates a full song in under 10 seconds on a regular RTX 3090 → Train it on your own sound: feed it about 8 of your own songs and it learns your style as a LoRA in about an hour Paste a genre and mood, get back a finished song with vocals, in any of 50+ languages.

Simplifying AI

16,640 Aufrufe • vor 1 Monat

Suno just got replaced entirely🤯 Someone built ACE-Step UI, a Spotify-style interface for ACE-Step 1.5 that generates full songs with vocals up to 4+ minutes, completely locally on your own GPU. 100% Free. Open-Source and Local

Suno just got replaced entirely🤯 Someone built ACE-Step UI, a Spotify-style interface for ACE-Step 1.5 that generates full songs with vocals up to 4+ minutes, completely locally on your own GPU. 100% Free. Open-Source and Local

Oliver Prompts

69,773 Aufrufe • vor 2 Monaten

Run ACE-Step-v1.5 on your computer, with 1 click. Do we finally have a true FREE SUNO alternative? Try yourself and find out! I wrote a 1-click launcher for the official Gradio app. It's high quality, fast, open source. Might be the LTX-2 moment for song generation AI!

Run ACE-Step-v1.5 on your computer, with 1 click. Do we finally have a true FREE SUNO alternative? Try yourself and find out! I wrote a 1-click launcher for the official Gradio app. It's high quality, fast, open source. Might be the LTX-2 moment for song generation AI!

cocktail peanut

54,227 Aufrufe • vor 8 Monaten

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

h100envy

710,481 Aufrufe • vor 2 Monaten

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

LMSYS Org

11,216 Aufrufe • vor 3 Monaten

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,962 Aufrufe • vor 3 Jahren

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Superman

285,151 Aufrufe • vor 2 Monaten

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Base Labs

243,932 Aufrufe • vor 1 Monat

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

QVAC

108,928 Aufrufe • vor 6 Monaten

$QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.$

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,413 Aufrufe • vor 5 Monaten

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 Aufrufe • vor 2 Monaten

Every time an AI video goes viral, someone asks the same thing: what was the prompt? Usually nobody knows. So I built a tool that finds out: It runs on MOSS-VL, open-weight 11B model (open source on GitHub: Upload a reference clip, it watches it frame by frame and reverse-engineers a generation prompt from what's actually in the video, not a guess. Refine it for a style, then generate something new from it. MOSS-VL is built for continuous video streams. Quantized versions deploy locally on a single RTX 4090, and it can be fine-tuned through LlamaFactory if you need it to understand something specific, like your own product's UI. I used the hosted API here, analyzing an uploaded clip instead of a live stream. Two ways to use it yourself: deploy it locally for real-time stream processing, or grab a free API key and use the hosted API on your own clips. API:

Every time an AI video goes viral, someone asks the same thing: what was the prompt? Usually nobody knows. So I built a tool that finds out: It runs on MOSS-VL, open-weight 11B model (open source on GitHub: Upload a reference clip, it watches it frame by frame and reverse-engineers a generation prompt from what's actually in the video, not a guess. Refine it for a style, then generate something new from it. MOSS-VL is built for continuous video streams. Quantized versions deploy locally on a single RTX 4090, and it can be fine-tuned through LlamaFactory if you need it to understand something specific, like your own product's UI. I used the hosted API here, analyzing an uploaded clip instead of a live stream. Two ways to use it yourself: deploy it locally for real-time stream processing, or grab a free API key and use the hosted API on your own clips. API:

Manish Kumar Shah

65,991 Aufrufe • vor 1 Monat

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇

Julian Goldie SEO

59,167 Aufrufe • vor 7 Monaten

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

ComfyUI

13,174 Aufrufe • vor 2 Monaten

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike

Harry Stebbings

63,738 Aufrufe • vor 3 Monaten

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,683 Aufrufe • vor 2 Jahren

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:

NVIDIA AI Developer

100,506 Aufrufe • vor 1 Jahr

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

Harman

48,089 Aufrufe • vor 3 Monaten

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Tom Greenwald

49,258 Aufrufe • vor 22 Tagen