Victor M's banner
Victor M's profile picture

Victor M

@victormustar • 32,509 subscribers

🤗 Head of Product @huggingface

Shorts

Fable has done AGI-level job on on the Boeing 747 benchmark... it's almost scary 👀

Fable has done AGI-level job on on the Boeing 747 benchmark... it's almost scary 👀

2,613,276 views

Finally spent 45 minutes with Grok 3 👀 Impression so far: it's the best code model I've ever used. I kept throwing random ideas at it and it grew the project to 400 lines almost error-free.

Finally spent 45 minutes with Grok 3 👀 Impression so far: it's the best code model I've ever used. I kept throwing random ideas at it and it grew the project to 400 lines almost error-free.

6,635,270 views

Drama-3 weights are available on the Hugging Face Hub 🔥 (+ official demo 👇)

Drama-3 weights are available on the Hugging Face Hub 🔥 (+ official demo 👇)

20,899 views

DeepSeek V4.1 Flash can build a "mechanically accurate pickup truck" in Blender quite well - soon to be run 100% locally 👀 the 🐳 has shipped something really unique here 🫶

DeepSeek V4.1 Flash can build a "mechanically accurate pickup truck" in Blender quite well - soon to be run 100% locally 👀 the 🐳 has shipped something really unique here 🫶

152,952 views

Funny how you can do the same thing with a local model without sending all your data to a remote cloud.

Funny how you can do the same thing with a local model without sending all your data to a remote cloud.

1,197,845 views

Before the week ends, let's acknowledge one of the most INSANE week ever for open AI, with 25+ notable open-weight drops across every modality: 🧠 LLMs → NVIDIA Nemotron 3 Ultra: 550B hybrid Mamba-MoE, only 55B active, 1M context, MMLU 89.1. NVFP4 variant claims ~5x throughput on Blackwell. First openly-weighted 550B hybrid Mamba-Transformer, closing the gap with frontier closed models. → Google Gemma 4 12B: fully open dense any-to-any (text/image/audio/video), 256k context, encoder-free, 140+ languages, AIME 2026 at 77.5. Shipped with a 23-checkpoint QAT wave (mobile ONNX + MLX). Most deployable model of the week. → StepFun Step-3.7-Flash: 198B sparse MoE VLM, ~11B active, SWE-Bench PRO 56.3. Apache 2.0. → Liquid AI LFM2.5-8B-A1B: edge MoE, just 1.5B active, 128k ctx, MATH500 88.8, MLX-ready. Best on-device option this week. → JetBrains Mellum2-12B-A2.5B-Thinking: their first open MoE, near-Qwen3-14B coding at 2.5B active. Apache 2.0. 🎨 Image gen (the surprise of the week) → Ideogram 4: their FIRST-EVER open weights. 9.3B flow-matching DiT trained from scratch. #2 overall behind GPT Image 2, top open-weight model on Design Arena + LMArena. Strongest open checkpoint for text-rich images, full stop. It has taste. Still can't believe this is open weights. 🔊 Audio & Speech (a breakout week for open TTS, 4 labs shipped) → Boson Higgs Audio v3 4B: 102 languages, 21 emotions, singing/whispering/shouting, sub-second TTFA. → RedNote dots.tts: the only fully continuous (no codec) open TTS pipeline, Apache 2.0. → Google Magenta RealTime 2: real-time music gen, <200ms latency, text+audio+MIDI. multimodalart ported it to PyTorch within hours with live ZeroGPU demos. → NVIDIA Nemotron-3.5 ASR: 600M streaming, 17x more concurrent streams vs Parakeet RNNT 1.1B. 👁️ Vision & VLMs → PaddleOCR-VL-1.6: SOTA document parsing at 1B params, Apache 2.0. → Baidu NAVA: 6.3B joint audio-video gen, best-in-class A/V sync, Apache 2.0. 🎬 Video, 3D & World Models → NVIDIA Cosmos3-Super: 64B omnimodal world model coupling action trajectories with video+audio gen, for Physical AI. → JD JoyAI-Echo: up to 5-min multi-shot text-to-video on LTX-2.3. → ByteDance Bernini-R + VAST TripoSplat (single-image-to-3D Gaussian splats, MIT).

Before the week ends, let's acknowledge one of the most INSANE week ever for open AI, with 25+ notable open-weight drops across every modality: 🧠 LLMs → NVIDIA Nemotron 3 Ultra: 550B hybrid Mamba-MoE, only 55B active, 1M context, MMLU 89.1. NVFP4 variant claims ~5x throughput on Blackwell. First openly-weighted 550B hybrid Mamba-Transformer, closing the gap with frontier closed models. → Google Gemma 4 12B: fully open dense any-to-any (text/image/audio/video), 256k context, encoder-free, 140+ languages, AIME 2026 at 77.5. Shipped with a 23-checkpoint QAT wave (mobile ONNX + MLX). Most deployable model of the week. → StepFun Step-3.7-Flash: 198B sparse MoE VLM, ~11B active, SWE-Bench PRO 56.3. Apache 2.0. → Liquid AI LFM2.5-8B-A1B: edge MoE, just 1.5B active, 128k ctx, MATH500 88.8, MLX-ready. Best on-device option this week. → JetBrains Mellum2-12B-A2.5B-Thinking: their first open MoE, near-Qwen3-14B coding at 2.5B active. Apache 2.0. 🎨 Image gen (the surprise of the week) → Ideogram 4: their FIRST-EVER open weights. 9.3B flow-matching DiT trained from scratch. #2 overall behind GPT Image 2, top open-weight model on Design Arena + LMArena. Strongest open checkpoint for text-rich images, full stop. It has taste. Still can't believe this is open weights. 🔊 Audio & Speech (a breakout week for open TTS, 4 labs shipped) → Boson Higgs Audio v3 4B: 102 languages, 21 emotions, singing/whispering/shouting, sub-second TTFA. → RedNote dots.tts: the only fully continuous (no codec) open TTS pipeline, Apache 2.0. → Google Magenta RealTime 2: real-time music gen, <200ms latency, text+audio+MIDI. multimodalart ported it to PyTorch within hours with live ZeroGPU demos. → NVIDIA Nemotron-3.5 ASR: 600M streaming, 17x more concurrent streams vs Parakeet RNNT 1.1B. 👁️ Vision & VLMs → PaddleOCR-VL-1.6: SOTA document parsing at 1B params, Apache 2.0. → Baidu NAVA: 6.3B joint audio-video gen, best-in-class A/V sync, Apache 2.0. 🎬 Video, 3D & World Models → NVIDIA Cosmos3-Super: 64B omnimodal world model coupling action trajectories with video+audio gen, for Physical AI. → JD JoyAI-Echo: up to 5-min multi-shot text-to-video on LTX-2.3. → ByteDance Bernini-R + VAST TripoSplat (single-image-to-3D Gaussian splats, MIT).

542,360 views

some genius invented a kebab benchmark for llms

some genius invented a kebab benchmark for llms

319,635 views

I just made my own Star Wars clip using AI (text-to-video)!

I just made my own Star Wars clip using AI (text-to-video)!

3,013,026 views

NVIDIA's Kimodo is the release of the week 🔥 Prompt the timeline whatever your want like: "a person walks forward" → "a person starts jumping", hit Generate, and watch a 3D character do it in seconds (700hrs of pro mocap training. Works on human + robot skeletons. Super fast + free to use on HF)

NVIDIA's Kimodo is the release of the week 🔥 Prompt the timeline whatever your want like: "a person walks forward" → "a person starts jumping", hit Generate, and watch a 3D character do it in seconds (700hrs of pro mocap training. Works on human + robot skeletons. Super fast + free to use on HF)

420,943 views

Decision 3.0 hype is real! it is the top performer in my little apple-harvesting test. It can actually play: read the scene, pick its own moves and collect apples without a pathfinding controller. Input: a screenshot of its surroundings, game stats and a short memory of its last four moves. It chooses up/down/left/right each turn. This run: 7 apples in 38 moves, zero damage 🔥

Decision 3.0 hype is real! it is the top performer in my little apple-harvesting test. It can actually play: read the scene, pick its own moves and collect apples without a pathfinding controller. Input: a screenshot of its surroundings, game stats and a short memory of its last four moves. It chooses up/down/left/right each turn. This run: 7 apples in 38 moves, zero damage 🔥

12,374 views

Reminder: every Hugging Face Space is an API your agents can call :) I asked mine to build a website about the flowers of France 🌸 and it used VAST AI's TripoSplat Space to turn photos it found into real 3D Gaussian splats, live on the page! All on my HF Pro daily ZeroGPU credits (40 min/day renewed daily for only $9/month)

Reminder: every Hugging Face Space is an API your agents can call :) I asked mine to build a website about the flowers of France 🌸 and it used VAST AI's TripoSplat Space to turn photos it found into real 3D Gaussian splats, live on the page! All on my HF Pro daily ZeroGPU credits (40 min/day renewed daily for only $9/month)

169,893 views

Crazy what you can do on Hugging Face in 40 seconds

Crazy what you can do on Hugging Face in 40 seconds

437,945 views

300tok/s on mobile is insane... open source must win ✊

300tok/s on mobile is insane... open source must win ✊

94,298 views

Why is a 100% open source chatbot faster than ChatGPT "Instant"? 👀

Why is a 100% open source chatbot faster than ChatGPT "Instant"? 👀

234,840 views

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B MoE refresh, Terminal-Bench 2.1 jumps 61.8→82.7 over the preview, DeepSWE 7.3→54.4. Closes in on Opus-4.8 on Agents' Last Exam (25.2 vs 25.7). MIT. → Muse-Glimmer-30B, from Meta (they are back!!): their first open agentic model. ~29.6B dense + perception encoder, 131k+ context, built to run fully local, no cloud. Apache 2.0. → Liquid AI LFM2.5-2.6B: 2.69B params, 131k context, 220 tok/s on an M5 Max in under 2.5GB RAM. Competitive with models 4x larger on agentic tasks. → inclusionAI Ling-3.0-flash: 124B total, only 5.1B active, ~12% the size of their old 1T flagship Ring-2.6, matches it on key benchmarks. MIT. → inclusionAI Ling-3.0-tiny: 7.9B total, 1.3B active, 86-90 tok/s on an M4 Pro MacBook at ~8GB peak memory. MIT. → NVIDIA Nemotron-3.5-Lightning-30B-A3B: hybrid Mamba-2+MoE+Attention, up to 1M context, runs on a single H100 or DGX Spark, SWE-bench Verified 52.8. → deepgrove maple-preview: 20B-A1B ternary-weight reasoner, 218 tok/s on a Mac mini M4, 5.3GB checkpoint. MIT. → BigBang-v1 (endless-frontier): fine-tuned from Qwen3.6-35B-A3B via a self-evolving generator/critic synthetic-data loop. Lands aggregate performance between DeepSeek V4 Flash (284B) and V4 Pro (1.6T), at 35B. Apache 2.0. 🎬 Video → MiniMax-H3: 33B dense omni model, native stereo audio, up to 2K/15s. 3.6k+ likes already. → Minimax-H3-Turbo (lightx2v): Apache-2.0 turbo distillation of H3 for fast inference. → Lightricks LTX-2.5: image-to-video update, custom Gemma-4-12B text encoder, a markedly stronger distilled model. 🔊 Voice → NVIDIA NemotronLabs VoiceChat-11B: full-duplex speech-to-speech, ~450ms turn-taking, #2 on open VoiceBench, and the first open full-duplex model with live tool-calling mid-conversation. 🛡️ Safety → Mistral Shieldstral-1.0-3B: 3B multimodal guardrail that takes your safety policy as plain text instead of fixed categories. Beats LlamaGuard-4-12B and ShieldGemma-9B on HarmBench (99.4) and ToxicChat (84.1) at a fraction of the size. Apache 2.0.

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B MoE refresh, Terminal-Bench 2.1 jumps 61.8→82.7 over the preview, DeepSWE 7.3→54.4. Closes in on Opus-4.8 on Agents' Last Exam (25.2 vs 25.7). MIT. → Muse-Glimmer-30B, from Meta (they are back!!): their first open agentic model. ~29.6B dense + perception encoder, 131k+ context, built to run fully local, no cloud. Apache 2.0. → Liquid AI LFM2.5-2.6B: 2.69B params, 131k context, 220 tok/s on an M5 Max in under 2.5GB RAM. Competitive with models 4x larger on agentic tasks. → inclusionAI Ling-3.0-flash: 124B total, only 5.1B active, ~12% the size of their old 1T flagship Ring-2.6, matches it on key benchmarks. MIT. → inclusionAI Ling-3.0-tiny: 7.9B total, 1.3B active, 86-90 tok/s on an M4 Pro MacBook at ~8GB peak memory. MIT. → NVIDIA Nemotron-3.5-Lightning-30B-A3B: hybrid Mamba-2+MoE+Attention, up to 1M context, runs on a single H100 or DGX Spark, SWE-bench Verified 52.8. → deepgrove maple-preview: 20B-A1B ternary-weight reasoner, 218 tok/s on a Mac mini M4, 5.3GB checkpoint. MIT. → BigBang-v1 (endless-frontier): fine-tuned from Qwen3.6-35B-A3B via a self-evolving generator/critic synthetic-data loop. Lands aggregate performance between DeepSeek V4 Flash (284B) and V4 Pro (1.6T), at 35B. Apache 2.0. 🎬 Video → MiniMax-H3: 33B dense omni model, native stereo audio, up to 2K/15s. 3.6k+ likes already. → Minimax-H3-Turbo (lightx2v): Apache-2.0 turbo distillation of H3 for fast inference. → Lightricks LTX-2.5: image-to-video update, custom Gemma-4-12B text encoder, a markedly stronger distilled model. 🔊 Voice → NVIDIA NemotronLabs VoiceChat-11B: full-duplex speech-to-speech, ~450ms turn-taking, #2 on open VoiceBench, and the first open full-duplex model with live tool-calling mid-conversation. 🛡️ Safety → Mistral Shieldstral-1.0-3B: 3B multimodal guardrail that takes your safety policy as plain text instead of fixed categories. Beats LlamaGuard-4-12B and ShieldGemma-9B on HarmBench (99.4) and ToxicChat (84.1) at a fraction of the size. Apache 2.0.

55,281 views

Microsoft TRELLIS.2 is here 🔥 • Single image → textured 3D mesh • 4B params, flow-matching transformer • Up to 1536³ resolution • Open weights, MIT licensed ⬇️ Demo available on Hugging Face

Microsoft TRELLIS.2 is here 🔥 • Single image → textured 3D mesh • 4B params, flow-matching transformer • Up to 1536³ resolution • Open weights, MIT licensed ⬇️ Demo available on Hugging Face

195,268 views

another open source win: opencode + GLM 4.6 is basically Claude Code (used it all day) but insanely cheap + better TUI. And you can use it with your Hugging Face token now 🔥

another open source win: opencode + GLM 4.6 is basically Claude Code (used it all day) but insanely cheap + better TUI. And you can use it with your Hugging Face token now 🔥

217,717 views

New Voxtral-4B-TTS is beautiful 💛 it sounds so good that it's whispering at closed models: "your time is over" - Demo available on Hugging Face ⬇️

New Voxtral-4B-TTS is beautiful 💛 it sounds so good that it's whispering at closed models: "your time is over" - Demo available on Hugging Face ⬇️

107,710 views

New Llama.cpp UI is a blessing for the local AI world 🌎 - Blazing fast, beautiful, and private (ofc) - Use 150,000+ GGUF models in a super slick UI - Drop in PDFs, images, or text documents - Branch and edit conversations anytime - Parallel chats and image processing - Math and code rendering - Constrained generation with JSON schema supported Easy setup + open-source + community-built 🔥

New Llama.cpp UI is a blessing for the local AI world 🌎 - Blazing fast, beautiful, and private (ofc) - Use 150,000+ GGUF models in a super slick UI - Drop in PDFs, images, or text documents - Branch and edit conversations anytime - Parallel chats and image processing - Math and code rendering - Constrained generation with JSON schema supported Easy setup + open-source + community-built 🔥

161,427 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Opus 5.5 designing LEGO 👀 I asked it to design a Microduck I can build with real LEGO pieces. It: > designed it life-size using 1113 real LEGO parts > verified: 3,204 connections, 0 collisions, every step buildable, centre of mass inside the feet 🤯 > made a 141-page LEGO-style booklet (237 steps) > priced every piece in the browser and prepared the orders on BrickLink
0:24
victormustar's profile picture

Opus 5.5 designing LEGO 👀 I asked it to design a Microduck I can build with real LEGO pieces. It: > designed it life-size using 1113 real LEGO parts > verified: 3,204 connections, 0 collisions, every step buildable, centre of mass inside the feet 🤯 > made a 141-page LEGO-style booklet (237 steps) > priced every piece in the browser and prepared the orders on BrickLink

Victor M

1,355,747 views • 23 days ago

Thanks Google, Embedding Gemma 2 is a big deal 🫶 Multimodal embeddings (text, images, video, audio) can run on-device in the browser. No server, no API key, ~20–70 ms per query on WebGPU. Everything stays on your machine (ofc). Now go build (new) things with it 🚀
0:36
victormustar's profile picture

Thanks Google, Embedding Gemma 2 is a big deal 🫶 Multimodal embeddings (text, images, video, audio) can run on-device in the browser. No server, no API key, ~20–70 ms per query on WebGPU. Everything stays on your machine (ofc). Now go build (new) things with it 🚀

Victor M

119,000 views • 11 days ago

Having so much fun with MinMax-H3. Cannot believe we now have this video quality 100% locally 🚀
0:52
victormustar's profile picture

Having so much fun with MinMax-H3. Cannot believe we now have this video quality 100% locally 🚀

Victor M

248,756 views • 2 months ago

Introducing: a coding agent (Pi) running entirely in your browser using a 2B model on WebGPU 🤯 MiniCPM5-2B + Pi, powered by Transformers.js + WebGPU + 4-bit ONNX weights. All previous attempt to create this failed but MiniCPM5 seems to make it usable. Available now on Hugging Face 👇
0:23
victormustar's profile picture

Introducing: a coding agent (Pi) running entirely in your browser using a 2B model on WebGPU 🤯 MiniCPM5-2B + Pi, powered by Transformers.js + WebGPU + 4-bit ONNX weights. All previous attempt to create this failed but MiniCPM5 seems to make it usable. Available now on Hugging Face 👇

Victor M

89,999 views • 1 month ago

DeepSeek-V4.1-Flash: the BEST Boeing benchmark result I’ve seen from an open-source model (by far). ✈️ It ran for hours with /goal. Where other models often stall quickly, it kept improving: inspect, spot a defect, zoom in, diagnose, fix, repeat. The video really shows how strong it is at sustaining that process over a long horizon (and how good it was at identifying what to work on). Impressive. Harness: Claude Code Prompt: "/goal create the most realistic boeing 747 using THREEJS - use your vision capatilities to create a self verifiable system, enter a loop until you are 100% satified about the result (you can build a camera system to inspect each angle)"
0:30
victormustar's profile picture

DeepSeek-V4.1-Flash: the BEST Boeing benchmark result I’ve seen from an open-source model (by far). ✈️ It ran for hours with /goal. Where other models often stall quickly, it kept improving: inspect, spot a defect, zoom in, diagnose, fix, repeat. The video really shows how strong it is at sustaining that process over a long horizon (and how good it was at identifying what to work on). Impressive. Harness: Claude Code Prompt: "/goal create the most realistic boeing 747 using THREEJS - use your vision capatilities to create a self verifiable system, enter a loop until you are 100% satified about the result (you can build a camera system to inspect each angle)"

Victor M

71,605 views • 1 month ago

Xiaomi-Robotics-1 just dropped on Hugging Face 🔥 A robot foundation model trained on 100,000 hours of real-world manipulation. They turned it loose in a real apartment: folding laundry, loading the washer, doing the dishes, packing a suitcase. Fully autonomous.
0:28
victormustar's profile picture

Xiaomi-Robotics-1 just dropped on Hugging Face 🔥 A robot foundation model trained on 100,000 hours of real-world manipulation. They turned it loose in a real apartment: folding laundry, loading the washer, doing the dishes, packing a suitcase. Fully autonomous.

Victor M

131,331 views • 2 months ago

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀 Qwen3.6-27B dense generation (on A10G): From 25 tok/s → 45 tok/s (+78%). Two flags on llama-server: --spec-type draft-mtp --spec-draft-n-max 2
0:38
victormustar's profile picture

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀 Qwen3.6-27B dense generation (on A10G): From 25 tok/s → 45 tok/s (+78%). Two flags on llama-server: --spec-type draft-mtp --spec-draft-n-max 2

Victor M

171,948 views • 5 months ago

GLM-5.1 > Claude Code (Opus 4.6)? I'm tripping or CC has become very bad but built a Three.js racing game to eval and it's extremely impressive. Thoughts: - One-shot car physics with real drift mechanics (this is hard) - My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen - 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters - All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio! - Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed You are going to hear about this model a lot in the next months - open source let's go 🚀🚀
0:25
victormustar's profile picture

GLM-5.1 > Claude Code (Opus 4.6)? I'm tripping or CC has become very bad but built a Three.js racing game to eval and it's extremely impressive. Thoughts: - One-shot car physics with real drift mechanics (this is hard) - My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen - 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters - All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio! - Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed You are going to hear about this model a lot in the next months - open source let's go 🚀🚀

Victor M

202,661 views • 6 months ago

Watch Gemma-4-E4B casually identify sea animals by classifying images in a single agentic session using its vision capabilities. (impressive for a 4B model 🚀) I'm convinced: the agents of tomorrow are local, free, fast, and run on every computer!
0:25
victormustar's profile picture

Watch Gemma-4-E4B casually identify sea animals by classifying images in a single agentic session using its vision capabilities. (impressive for a 4B model 🚀) I'm convinced: the agents of tomorrow are local, free, fast, and run on every computer!

Victor M

171,614 views • 6 months ago

LTX-2 trainer is a huge deal. I tried it to add water to the podracers scene using their demo water-sim fine-tune (it's a fine-tune whose only goal is to add water :D) I think we're going to see film productions that don't use general models. They'll train their own fine-tunes, built for exactly what they need and consistent between shots for long content.
1:05
victormustar's profile picture

LTX-2 trainer is a huge deal. I tried it to add water to the podracers scene using their demo water-sim fine-tune (it's a fine-tune whose only goal is to add water :D) I think we're going to see film productions that don't use general models. They'll train their own fine-tunes, built for exactly what they need and consistent between shots for long content.

Victor M

94,903 views • 3 months ago

Why is a 100% open source chatbot faster so much faster then ChatGPT to turn an image into anime? 👀
0:30
victormustar's profile picture

Why is a 100% open source chatbot faster so much faster then ChatGPT to turn an image into anime? 👀

Victor M

205,569 views • 11 months ago

My last hours with Fable: I was building this movement parkour sim before it went down... Impressed by its autonomy: built its own self-verifying harness with its own rubric for how a movement should feel. When a new movement was added it could tell on its own what felt right or wrong until it felt 100% right without me in the loop (and it was very good at it) Fable was more than just another model iteration imo. For the short (but intense) time it was available, it felt like playing with clay: ideas became code with almost no friction and the line between both became blurry. More than ever: open source MUST win. I don't want a world where intelligence is centralized and you're stuck with a hand saw while others have a chainsaw.
0:27
victormustar's profile picture

My last hours with Fable: I was building this movement parkour sim before it went down... Impressed by its autonomy: built its own self-verifying harness with its own rubric for how a movement should feel. When a new movement was added it could tell on its own what felt right or wrong until it felt 100% right without me in the loop (and it was very good at it) Fable was more than just another model iteration imo. For the short (but intense) time it was available, it felt like playing with clay: ideas became code with almost no friction and the line between both became blurry. More than ever: open source MUST win. I don't want a world where intelligence is centralized and you're stuck with a hand saw while others have a chainsaw.

Victor M

82,975 views • 4 months ago

Open source AI music is actually good now 🔥 Made a free demo for ACE-Step 1.5: describe any song, get it back in seconds ⤵️
1:04
victormustar's profile picture

Open source AI music is actually good now 🔥 Made a free demo for ACE-Step 1.5: describe any song, get it back in seconds ⤵️

Victor M

99,911 views • 6 months ago

This is wild 🤯 We finally have an open-source music generation model that rocks 🚀
0:56
victormustar's profile picture

This is wild 🤯 We finally have an open-source music generation model that rocks 🚀

Victor M

248,949 views • 1 year ago

DeepSeek V4.1 Flash is available in HuggingChat 🐋 (absolute must try if you have a HF account!)
0:22
victormustar's profile picture

DeepSeek V4.1 Flash is available in HuggingChat 🐋 (absolute must try if you have a HF account!)

Victor M

20,727 views • 1 month ago

Hugging Face is (also) the best place to write about AI. > Your articles are now automatically linked from your model pages, so anyone looking at the model finds what you wrote about it. > We shipped an improved UX to make writing, drafting and publishing better. > We made it great to use as a team: add coauthors to work together and have everyone credited on the post. Get HF Pro at $9/month or subscribe your org to Team or Enterprise to get started.
0:22
victormustar's profile picture

Hugging Face is (also) the best place to write about AI. > Your articles are now automatically linked from your model pages, so anyone looking at the model finds what you wrote about it. > We shipped an improved UX to make writing, drafting and publishing better. > We made it great to use as a team: add coauthors to work together and have everyone credited on the post. Get HF Pro at $9/month or subscribe your org to Team or Enterprise to get started.

Victor M

18,021 views • 1 month ago

Why isn't everyone using FLUX.2-dev-Turbo? Top quality, great at editing, 1.5s/image speed, 120 images for $1. My go-to for AI image gen/editing now 🔥
0:26
victormustar's profile picture

Why isn't everyone using FLUX.2-dev-Turbo? Top quality, great at editing, 1.5s/image speed, 120 images for $1. My go-to for AI image gen/editing now 🔥

Victor M

78,040 views • 9 months ago

New TTS bomb dropped on Hugging Face. It has multispeaker support and the output quality looks amazing 🤯
0:23
victormustar's profile picture

New TTS bomb dropped on Hugging Face. It has multispeaker support and the output quality looks amazing 🤯

Victor M

112,653 views • 1 year ago

🤯 Mind blown by the realism of podcasts generated by NotebookLM...
6:45
victormustar's profile picture

🤯 Mind blown by the realism of podcasts generated by NotebookLM...

Victor M

165,977 views • 2 years ago

DeepSite V2 just dropped (insane for Vibe Coding) 🤯 🔹Amazingly good at UI Design 🔹DeepSeek-R1 model now available 🔹Targeted Edits on any element 🔹Redesign any existing website 🔹100% open source (UI + models)
0:36
victormustar's profile picture

DeepSite V2 just dropped (insane for Vibe Coding) 🤯 🔹Amazingly good at UI Design 🔹DeepSeek-R1 model now available 🔹Targeted Edits on any element 🔹Redesign any existing website 🔹100% open source (UI + models)

Victor M

105,886 views • 1 year ago