Hi3D v1.0 takes a rough 3D mesh and refines it into high-res geometry 🗿
Image in → coarse mesh → 1M-face refined mesh, conditioned on the image. Panel lines, vents, teeth, hydraulics.
hf.co/spaces/hugging…
Image in → coarse mesh → 1M-face refined mesh, conditioned on the image. Panel lines, vents, teeth, hydraulics.
hf.co/spaces/hugging…
0
10
86
4,423
Hugging Apps retweeted
FastVideo's @MiniMax_AI FastH3 Omni model is now available on @huggingface spaces! Try it! Up to 9 reference images, 3 videos, and 3 audio clips!
Thanks to @multimodalart for adding support!
huggingface.co/spaces/FastVid…
Thanks to @multimodalart for adding support!
huggingface.co/spaces/FastVid…
0
5
13
770
A 4B vision model that points at what it's talking about 🕶️
Xiaomi-Lens-0 answers in plain language, and every object it mentions comes with its own segmentation mask.
hf.co/spaces/SeerRay…
Xiaomi-Lens-0 answers in plain language, and every object it mentions comes with its own segmentation mask.
hf.co/spaces/SeerRay…
0
5
46
2,303
DuET: piano audio → sheet music 🎹
DuET transcribes a piano recording straight into an engraved score: notes, chords, key and time signature 🎵
🎶 hf.co/spaces/Wayne42…
DuET transcribes a piano recording straight into an engraved score: notes, chords, key and time signature 🎵
🎶 hf.co/spaces/Wayne42…
0
5
47
3,237
Hugging Apps retweeted
yay! FastH3 Omni is now open weights! 📹
high quality 8 step reference-to-video, fully end-to-end open source (including training code)
this is the model many said rivals fal's H3 Max 👀
▶️ on Spaces huggingface.co/spaces/hugging…
📁 Model huggingface.co/collections/Fa…
high quality 8 step reference-to-video, fully end-to-end open source (including training code)
this is the model many said rivals fal's H3 Max 👀
▶️ on Spaces huggingface.co/spaces/hugging…
📁 Model huggingface.co/collections/Fa…
As promised, FastVideo open-sources @MiniMax_AI FastH3 Omni, training code included! 🚀
- Real-time gen @ 12x faster on NVIDIA Blackwell
- NVFP4/FP8 for Spark + RTX!
- ComfyUI day-0
Collab with @NVIDIAAI , Nuva Lab @nuvalab and Reactor @reactorworld
Open source must win! ♥️
5
2
29
3,298
Shoot first, focus later 📷
FlashReFocus restores a photo focus for the entire image, then refocuses wherever you click, in ~0.6 s per click.
▶️ hf.co/spaces/ming053…
FlashReFocus restores a photo focus for the entire image, then refocuses wherever you click, in ~0.6 s per click.
▶️ hf.co/spaces/ming053…
0
3
29
1,751
BRIA dropped FIBO 2.0 Edit Turbo on @huggingface edits images precisely in only 4 steps ⚡
One instruction, converted into a precise json, up to 4 reference images, or a mask to change focus in one area
▶️ on Spaces
hf.co/spaces/briaai/…
One instruction, converted into a precise json, up to 4 reference images, or a mask to change focus in one area
▶️ on Spaces
hf.co/spaces/briaai/…
2
0
11
1,302
FLUX.3 Image Klein 6B just dropped on @huggingface 🔥
Base and distilled (16 steps), multi-reference editing, JSON bounding-box layouts
play with it 👇
hf.co/spaces/black-f…
Base and distilled (16 steps), multi-reference editing, JSON bounding-box layouts
play with it 👇
hf.co/spaces/black-f…
4
19
198
15,506
Hugging Apps retweeted
ICYMI: Lightx2v just dropped Qwen Image 2.1 Lightning ⚡️
> 4-step distilled LoRA
> weights: huggingface.co/lightx2v/Qwen-…
> space: huggingface.co/spaces/hugging…
> 4-step distilled LoRA
> weights: huggingface.co/lightx2v/Qwen-…
> space: huggingface.co/spaces/hugging…
0
14
155
7,888
Hugging Apps retweeted
New H3 character swap LoRA🔥
amazing work from @Alissonerdx
LoRA: huggingface.co/Alissonerdx/Mi…
Space:
huggingface.co/spaces/linoyts…
amazing work from @Alissonerdx
LoRA: huggingface.co/Alissonerdx/Mi…
Space:
huggingface.co/spaces/linoyts…
18
56
721
39,944
one photo, new camera angles 📷
this Qwen-Image-2.1 LoRA by @_akhaliq using the ML Intern reshoots a subject from a camera position you pick: close-up, high angle, straight down, from behind. no background
▶️ on Spaces hf.co/spaces/hugging…
this Qwen-Image-2.1 LoRA by @_akhaliq using the ML Intern reshoots a subject from a camera position you pick: close-up, high angle, straight down, from behind. no background
▶️ on Spaces hf.co/spaces/hugging…
4
46
402
17,478
Qwen Image 2.1 Turbo just landed on @huggingface
8 steps, same quality
▶️ on Spaces huggingface.co/spaces/hugging…
8 steps, same quality
▶️ on Spaces huggingface.co/spaces/hugging…
15
35
449
29,159
pose a mannequin, anyone takes the pose 🕺
the VNCCS PoseStudio LoRA for Qwen-Image-2.1 redraws any character in the exact pose of a 3D mannequin, keeping their face, clothes and art style
▶️ on Spaces hf.co/spaces/hugging…
the VNCCS PoseStudio LoRA for Qwen-Image-2.1 redraws any character in the exact pose of a 3D mannequin, keeping their face, clothes and art style
▶️ on Spaces hf.co/spaces/hugging…
1
9
68
6,699
native 4K video, from a 1.3B model 🔍
T3-Video retrofits Wan2.1-1.3B with window attention so it generates directly in 3840×2176, no upscaler: zoom in and every bush is still there
▶️ on Spaces hf.co/spaces/hugging…
T3-Video retrofits Wan2.1-1.3B with window attention so it generates directly in 3840×2176, no upscaler: zoom in and every bush is still there
▶️ on Spaces hf.co/spaces/hugging…
7
41
453
24,334
Kokoro TTS, but 10× smaller 🫰
Paradee distills Kokoro-82M into a 8M-param TTS
just 9 MB of weights can speak faster than real time on a single CPU thread and runs on your toaster
▶️ on Spaces hf.co/spaces/hugging…
Paradee distills Kokoro-82M into a 8M-param TTS
just 9 MB of weights can speak faster than real time on a single CPU thread and runs on your toaster
▶️ on Spaces hf.co/spaces/hugging…
17
111
1,093
89,418
@HuggingApps hey thanks for making this space! if you're interested in learning more about how I distilled Kokoro I have an interactive blog post here sahilmahendrakar.com/writings/parad… and a paper here arxiv.org/pdf/2610.06817
0
0
5
3,843
Hugging Apps retweeted
Doing video background replacement with H3 Inpainting + LTX Alpha Matte LoRA, and it's surprisingly good 🔥
> LTX 2.5 LoRA to extract matte
> H3 Ref inpainting (+ Turbo LoRA) to generate a new background
> Mask drop knob to reduce flickering and improve lighting match - drops the inpaiadded the workflow to 🧨diffusers modular + built Spaces for it 👇
> LTX 2.5 LoRA to extract matte
> H3 Ref inpainting (+ Turbo LoRA) to generate a new background
> Mask drop knob to reduce flickering and improve lighting match - drops the inpaiadded the workflow to 🧨diffusers modular + built Spaces for it 👇
2
26
220
22,000
240p mush in, crisp 720p out ✨
a restoration LoRA for LTX-2.5 by CQdesign rebuilds faces, skin and fingers from degraded video
▶️ on Spaces hf.co/spaces/hugging…
a restoration LoRA for LTX-2.5 by CQdesign rebuilds faces, skin and fingers from degraded video
▶️ on Spaces hf.co/spaces/hugging…
3
26
240
11,465