apolinario (poli)'s banner
apolinario (poli)'s profile picture

apolinario (poli)

@multimodalart • 16,147 subscribers

ML Engineer for Art and Creativity @HuggingFace ([email protected])

Shorts

MiniMax H3 image+audio to video feed an audio into h3 instead of generating it. i was testing this flow, got shocked with how good the lipsync and movement is implemented it on the i2v version in diffusers, made a demo for it. what do you think? 🔊 ▶️

MiniMax H3 image+audio to video feed an audio into h3 instead of generating it. i was testing this flow, got shocked with how good the lipsync and movement is implemented it on the i2v version in diffusers, made a demo for it. what do you think? 🔊 ▶️

23,194 views

Boring Reality LoRA just dropped for HunyuanVideo 🏙️🏞️ A fine-tune that lead not to cinematic shots, but to something that could've come out of your phone 📱

Boring Reality LoRA just dropped for HunyuanVideo 🏙️🏞️ A fine-tune that lead not to cinematic shots, but to something that could've come out of your phone 📱

407,400 views

testing out the Diffusers Image Fill demo capabilities on a random image

testing out the Diffusers Image Fill demo capabilities on a random image

274,371 views

Qwen Image Multiple Angles LoRA is an exquisitely trained LoRA! 📐˚₊‧꒰ა Keep character and scenes consistent, and flies the camera around! Open source got there! One of the best LoRAs I've come across lately 🙌

Qwen Image Multiple Angles LoRA is an exquisitely trained LoRA! 📐˚₊‧꒰ა Keep character and scenes consistent, and flies the camera around! Open source got there! One of the best LoRAs I've come across lately 🙌

121,656 views

GPUs for all 🤗 Creating ZeroGPU demos or apps is now available to ALL Hugging Face users tell your agent: "Build a HF ZeroGPU demo for this model" New Space: Agent skill:

GPUs for all 🤗 Creating ZeroGPU demos or apps is now available to ALL Hugging Face users tell your agent: "Build a HF ZeroGPU demo for this model" New Space: Agent skill:

24,719 views

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality

41,668 views

I just built a demo for this Light Migration LoRA on Hugging Face the quality surprises me on every output 🤯

I just built a demo for this Light Migration LoRA on Hugging Face the quality surprises me on every output 🤯

80,276 views

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

29,948 views

Apply Texture Qwen Image Edit LoRA by tarn59 works with EVERYTHING! 👉🪵🧶, this model trains so well I've built this demo so you can apply *any* texture to *any* object on Hugging Face

Apply Texture Qwen Image Edit LoRA by tarn59 works with EVERYTHING! 👉🪵🧶, this model trains so well I've built this demo so you can apply *any* texture to *any* object on Hugging Face

67,831 views

Introducing Kontext Relight! 💡 ✨ A FLUX Kontext Relight LoRA + demo trained for state-of-the art relighting for subjects & landscapes

Introducing Kontext Relight! 💡 ✨ A FLUX Kontext Relight LoRA + demo trained for state-of-the art relighting for subjects & landscapes

76,088 views

LLaDA (the first Large Language Diffusion Model) is *just* out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇

LLaDA (the first Large Language Diffusion Model) is *just* out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇

82,599 views

Excited to introduce LEDITS++, a novel way to edit real images with precision ✏️ - Multiple edits ✂️🔁 - Automagic free masking 🪄🎭 - 🆕 DPM-Solver fast inversion 🔀⚡ 🤗 Try it: 🔗 Project: 📝 Paper

Excited to introduce LEDITS++, a novel way to edit real images with precision ✏️ - Multiple edits ✂️🔁 - Automagic free masking 🪄🎭 - 🆕 DPM-Solver fast inversion 🔀⚡ 🤗 Try it: 🔗 Project: 📝 Paper

131,559 views

introducing the media synthesis museum an active and interactive entity created to preserve generative cultural objects it starts as a Hugging Face organization that contains modern code for old techniques: VQGAN+CLIP, DALL-E Mini, ModelScope Video, Stable Diffusion 1.5 you can use old models/technique directly on Spaces or locally on modern hardware/software, without the old "colab notebook" dependency rot the idea is to really preserve and make accessible those artifacts and aesthetics - both open source. In the future, we hope to also have also historically relevant closed source like DALL-E 1 and DALL-E 2 from OpenAI, older Midjourney models, older Runway apps/techniques/models (cc Cristóbal Valenzuela David Sam Altman)

introducing the media synthesis museum an active and interactive entity created to preserve generative cultural objects it starts as a Hugging Face organization that contains modern code for old techniques: VQGAN+CLIP, DALL-E Mini, ModelScope Video, Stable Diffusion 1.5 you can use old models/technique directly on Spaces or locally on modern hardware/software, without the old "colab notebook" dependency rot the idea is to really preserve and make accessible those artifacts and aesthetics - both open source. In the future, we hope to also have also historically relevant closed source like DALL-E 1 and DALL-E 2 from OpenAI, older Midjourney models, older Runway apps/techniques/models (cc Cristóbal Valenzuela David Sam Altman)

11,143 views

GANs are so back?! Scientists from Brown and Cornell have published a paper with a ✨ modern architecture GAN ✨ that is 🗿 stable to train 🗿 and competitive with SOTA GANs and even diffusion models Paper and demo 👇

GANs are so back?! Scientists from Brown and Cornell have published a paper with a ✨ modern architecture GAN ✨ that is 🗿 stable to train 🗿 and competitive with SOTA GANs and even diffusion models Paper and demo 👇

64,122 views

Editing facial expressions in real time now on Hugging Face Spaces 👨‍🎤🔀 A Grog converted Cog image to Gradio running a ComfyUI backend - magic of open source 🤝 ▶️

Editing facial expressions in real time now on Hugging Face Spaces 👨‍🎤🔀 A Grog converted Cog image to Gradio running a ComfyUI backend - magic of open source 🤝 ▶️

71,701 views

You can now finally create your own stock photo smiling while eating salad in seconds 👨‍🎤🥗 IP-Apdater-FaceID Plus was silently released last week - it's first inference technique time face really captures my likeness 🥸🦚 ▶️

You can now finally create your own stock photo smiling while eating salad in seconds 👨‍🎤🥗 IP-Apdater-FaceID Plus was silently released last week - it's first inference technique time face really captures my likeness 🥸🦚 ▶️

60,745 views

The Dream 7B (diffusion reasoning language model) is OUT! 🚨 I built a demo so you can test it out (and check the diffusion process live) 𖣯🔍

The Dream 7B (diffusion reasoning language model) is OUT! 🚨 I built a demo so you can test it out (and check the diffusion process live) 𖣯🔍

35,679 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

i created microduck AR visualization so you can already see how it will look in your home and play a bit with it 🦆 link and instructions ⤵️
0:29
multimodalart's profile picture

i created microduck AR visualization so you can already see how it will look in your home and play a bit with it 🦆 link and instructions ⤵️

apolinario (poli)

30,723 views • 4 days ago

MiniMax Music 3 is just out on Hugging Face 🎶🎵 SoTA song generation, now open weights 🔊, a 8B LLM + 2.7B DiT that turn prompt + lyrics into full songs fits smol consumer GPUs with 🧨 diffusers or comfy model weights + app on Spaces, come play ▶️
0:27
multimodalart's profile picture

MiniMax Music 3 is just out on Hugging Face 🎶🎵 SoTA song generation, now open weights 🔊, a 8B LLM + 2.7B DiT that turn prompt + lyrics into full songs fits smol consumer GPUs with 🧨 diffusers or comfy model weights + app on Spaces, come play ▶️

apolinario (poli)

63,108 views • 19 days ago

before the horse there was the foal
0:33
multimodalart's profile picture

before the horse there was the foal

apolinario (poli)

11,127 views • 3 days ago

I' m so addicted to Google Magenta Project RealTime 2 🎹 so to justify playing with it 24/7 I ported the real-time apps to Hugging Face Spaces 🤗 (and ported the entire lib to pytorch/transformers too) Play live in real time on
0:31
multimodalart's profile picture

I' m so addicted to Google Magenta Project RealTime 2 🎹 so to justify playing with it 24/7 I ported the real-time apps to Hugging Face Spaces 🤗 (and ported the entire lib to pytorch/transformers too) Play live in real time on

apolinario (poli)

35,185 views • 2 months ago

ok, is this it?! I just tested the DreamO demo and it's a framework for FLUX that can kind of do it all 🪄🔧 👨‍🎤 A really good FLUX ID preservation reference 🎨 IP Adapter for composition and style 👗 Virtual Try-on ... and more!
0:25
multimodalart's profile picture

ok, is this it?! I just tested the DreamO demo and it's a framework for FLUX that can kind of do it all 🪄🔧 👨‍🎤 A really good FLUX ID preservation reference 🎨 IP Adapter for composition and style 👗 Virtual Try-on ... and more!

apolinario 🌐

66,682 views • 1 year ago

Less than 1 minute guide on how to train your own LoRA with LoRA Ease 🧞‍♂️⚡ Train high-quality LoRAs on objects 📦, faces 😊, styles 🎨 or characters 🧑‍🎤 effortlessly and super cheap ༄ ▶️
0:59
multimodalart's profile picture

Less than 1 minute guide on how to train your own LoRA with LoRA Ease 🧞‍♂️⚡ Train high-quality LoRAs on objects 📦, faces 😊, styles 🎨 or characters 🧑‍🎤 effortlessly and super cheap ༄ ▶️

apolinario (poli)

90,981 views • 2 years ago

PRO for PROs Nano Banana PRO is available at no cost for Hugging Face PRO subscribers on Spaces, go bananas 🍌
0:21
multimodalart's profile picture

PRO for PROs Nano Banana PRO is available at no cost for Hugging Face PRO subscribers on Spaces, go bananas 🍌

apolinario 🌐

32,519 views • 9 months ago

Thanks Miguel | AP for merging my PR to add high resolution to the Illusion Diffusion Space 📺🌀 It's now as fast, double the resolution and has crispy details - go play ▶️
0:21
multimodalart's profile picture

Thanks Miguel | AP for merging my PR to add high resolution to the Illusion Diffusion Space 📺🌀 It's now as fast, double the resolution and has crispy details - go play ▶️

apolinario (poli)

69,284 views • 2 years ago

Introducing FLUX LoRA the Explorer 🧭✨ Explore, generate and download FLUX LoRAs! 🖼️ Including the popular flux-realism and the cute Frosting Lane Come over, we're just getting started 🛸 ▶️
0:26
multimodalart's profile picture

Introducing FLUX LoRA the Explorer 🧭✨ Explore, generate and download FLUX LoRAs! 🖼️ Including the popular flux-realism and the cute Frosting Lane Come over, we're just getting started 🛸 ▶️

apolinario (poli)

48,852 views • 2 years ago

Having fun with computer vision! 👁️ Converted 🤗 image → 3D, then dragged to AA's 3d model playground
0:40
multimodalart's profile picture

Having fun with computer vision! 👁️ Converted 🤗 image → 3D, then dragged to AA's 3d model playground

apolinario (poli)

20,221 views • 1 year ago

How different quantization affects FLUX.2 models outputs? Check out on the diffusers + FLUX.2 interactive carousel on the blog
0:27
multimodalart's profile picture

How different quantization affects FLUX.2 models outputs? Check out on the diffusers + FLUX.2 interactive carousel on the blog

apolinario 🌐

12,540 views • 9 months ago

No more content to load