Tweeting the coolest apps and demos on @huggingface Spaces curation by @multimodalart
- Tweets 167
- Following 3
- Followers 4,598
- Likes 197
Hugging Apps retweeted
This is native Qwen Image 2.1, no LoRA - move and resize objects seamlessly in an image🔥
I was planning to finetune on this task to showcase the new 🧨 diffusers LoRA support for Qwen 2.1 (go try it!), but while testing the base model I realized it's actually so good at it out of the box (pun intended haha)
Try it ▶️ huggingface.co/spaces/linoyt…
Train 🧨 github.com/huggingface/diffu…
6
55
516
42,618
one PNG in, every angle out 🔄
a viewpoint-orbit LoRA for Qwen-Image-2.1: upload one transparent image and it walks the camera around the object, back view included, transparency kept
▶️ on Spaces hf.co/spaces/ML-Intern-lab/Q…
14
31
244
13,621
Hugging Apps retweeted
I'm loving the character swap LoRA for H3, I think it might be even better than animate and inpainting
huggingface.co/spaces/huggin…
3
27
299
19,880
This LoRA was trained fully autonomously by an agent, using the Hugging Face ML Intern system
Give Qwen-Image 2.1 one transparent cutout and say "rotate the camera 90 degrees to the right".
It hands back the same object from the new angle, still transparent. No background removal, no 3D model.
A LoRA, trained by ML-Intern for under $20. 🧵
9
12
860
box it, and it's gone 🗑️
an object-remover LoRA by @prithivMLmods for Qwen-Image-2.1, stacked with Viggle's turbo: draw a box over the tourist, the bike or the boat, and it's erased in 6 steps
▶️ on Spaces hf.co/spaces/hugging-apps/qw…
7
11
78
4,248
2 STEP LORA?!
finally music LoRAs are picking up! here's YuE2 trailer music ⚔️
the Two Steps From Hell LoRA by monsterovich makes YuE2 write huge cinematic anthems: 3 minutes, full orchestra and vocals, from your lyrics
▶️ on Spaces hf.co/spaces/hugging-apps/yu…
1
3
26
2,701
medical ai keeps advancing, now you can take the bones out of a chest X-ray 🩻
@qure_ai released a model that splits a radiograph into soft tissue, bone and lungs, so the ribs stop hiding what's behind them
▶️ on Spaces hf.co/spaces/hugging-apps/bo…
7
39
269
14,166
it's a decomposition technique based on this paper
huggingface.co/papers/2609.2… which is currently under peer-review
huggingface.co/qureaiorg/bon…
1
8
328
finally music LoRAs are picking up! here's YuE2 trailer music ⚔️
the Two Steps From Hell LoRA by monsterovich makes YuE2 write huge cinematic anthems: 3 minutes, full orchestra and vocals, from your lyrics
▶️ on Spaces hf.co/spaces/hugging-apps/yu…
8
12
116
8,978
Alibaba just dropped ControlNet Union for Qwen-Image-2.1 🕹️
one checkpoint for canny, depth, pose, lineart, scribble & more: keep the structure of any photo or pose, re-imagine everything else
▶️ on Spaces hf.co/spaces/hugging-apps/qw…
1
24
223
14,813
Apple just dropped LensVLM 9B on Hugging Face 🍎
a novel kind of VLM that reads long documents the way you skim a book: it glances at every page as a tiny image, then opens only the pages that hold the answer 🔍
▶️ on Spaces hf.co/spaces/hugging-apps/le…
1
6
18
4,954
Paper: arxiv.org/abs/2605.07019
Model: huggingface.co/apple/LensVLM…
318
1/ You can now try Cua-S1-4B-0.2 in your browser. Thanks to @multimodalart at @huggingface for building the Space!
Pick an example and see how the model scores the candidate actions.
huggingface.co/spaces/huggin…
1/ Today we're introducing Cua-S1-4B-0.2, the first multimodal decision model trained with RLOO on live computer-use tasks, using task-completion rewards.
Text and multimodal adapters are available under Apache-2.0: github.com/trycua/cua
huggingface.co/cua-ai/cua-s1…
6
26
200
14,586
Hugging Apps retweeted
this is fun
huggingface.co/spaces/huggin…
Speech recognition is easy—until you ask it to listen forever.
Today we’re open-sourcing Audio8 ASR Infinite:
Ultra-low latency, unlimited audio, 24/7 transcription, no drift.
Built-in semantic turn detection keeps it listening like a human ear.
New SOTA for streaming ASR.
6
29
340
29,996
We launched the first Qwen-Image-2.1 turbo for the open community.
Try Viggle-Turbo, a DMD-distilled Qwen-Image-2.1 that generates and edits in 4 sampling steps, with no classifier-free guidance.
Weights: huggingface.co/Viggle/Qwen-I…
Qwen-Image-2.1 in 4 steps is here ⚡
@ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model
▶️ on Spaces hf.co/spaces/Viggle/Qwen-Ima…
10
17
97
9,980
Qwen-Image-2.1 in 4 steps is here ⚡
@ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model
▶️ on Spaces hf.co/spaces/Viggle/Qwen-Ima…
12
114
1,366
94,018
Hugging Apps retweeted
I added an interactive component so you can manually adjust the camera angles with Viggle's H3 Meridian (works both for image and video)
huggingface.co/spaces/linoyt…
2
19
186
9,870
Hugging Apps retweeted
Introducing the Decision Index 0.1 ⚖️
a rigorous leaderboard comparing jev with 30+ open weights decision models
35+ benchmarks. asking 130K questions to each model
testing knowledge 🧠, automation ⚙️, understanding 🤔and even creativity 🎨
huggingface.co/spaces/multim…
28
52
312
43,449