Background removal for the hard cases ✂
@bria_ai_'s RMBG 3.0 ranks #1 in background removal for the hard edits: lifts out backlit hair, bike spokes, dandelion wisps, even a spinning helicopter rotor, and you can drop them onto any new scene
▶️ hf.co/spaces/briaai/BRIA-RMB…
ICYMI: LongCat-Video-Avatar-1.6 just landed on @huggingface 🔥
upgrades vs v1.5:
> more natural lip animation & improved audio synchronization
> better for long video generation
> new optimizations for faster inference
took it for a spin with portraits from a funky Krea 2 LoRA by @akatz_ai + audio by Drama 3
weights: huggingface.co/meituan-longc…
space: huggingface.co/spaces/victor…
Someone trained a GTA world model from scratch before GTA VI 🤯
starting from one screenshot, hold WASD, frames are all generated live, ~17 fps on a single RTX 4060 Ti, 30 fps on better gpus
▶️ streamed to your browser on @huggingfacehf.co/spaces/lucidml/gta
Official @MiniMax_AI H3 Image just landed on Hugging Face 🎨
Generate or edit images (up to reference 8 images) in just 6 steps. 4K generation supported
been a while since an image model didn't excite me this much! the aesthetics are fresh!
▶️ hf.co/spaces/MiniMaxAI/minim…
Pika Labs @pika_labs just dropped their first ever open-weights model 🐇🔊
Pika H3 Flex is a MiniMax H3 post-train that is surpassed H3 and H3 Max, while being 6-step and open source 🔥
▶️ huggingface.co/spaces/Pika-L…
Today, we open-source v0.2 of P-Q-Image-2.1, two new 6-step LoRA adapters for Qwen-Image-2.1 by @Alibaba_Qwen. The first distillation that removes the prompt-upsampling step!
- 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images in just 6 steps instead of 40. Use 6-steps for preserving inputs when editing and 6-steps-upsampled for improved visual quality and shorter end-to-end generation.
- 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? 6-step distillation provides improved quality with few generation steps. 6-steps-upsampled is the first distillation that removes the need for a separate prompt-upsampling step. This means 41 to 80 seconds saved, depending on your prompt style.
- 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸? The LoRA adapters load directly on top of Qwen-Image-2.1, so the pipeline stays unchanged. Few-step distillation cuts the diffusion cost, and the upsampled adapter also removes the prompt-upsampling step before image generation.
🤗 Open Weights: huggingface.co/PrunaAI/P-Q-I…
👉 HF Space: huggingface.co/spaces/PrunaA…
Qwen-Image-2.1 is now real time ⚡
This 2-step DMD2 LoRA by @linoy_tsaban allows for live text-to-image and live editing on 4090, 5090 or on Spaces via ZeroGPU.
▶️ hf.co/spaces/linoyts/qwen-im…
Introducing Qwen Image 2.1 Realtime ⚡️
I'm releasing V1 of my *2-step* distilled LoRA, and it runs in *realtime* on ZeroGPU ⚡️⚡️
(live editing part of the video was not sped up!)
> DMD2, rank 32
> 2 steps, with quality competitive with Turbo (8-step) and Base (40-step)
> realtime on ZeroGPU (half of an RTX Pro 6000)
LoRA: huggingface.co/linoyts/Qwen-…
Space: huggingface.co/spaces/linoyt…
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-apps/hi…
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-Lab/xia…
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-de…
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/huggin…
📁 Model huggingface.co/collections/F…
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/ming0531/FlashR…