Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 4 hours ago

hugging-apps/kanana-2-v-decide-3b

multimodalart updated a Space about 4 hours ago

hugging-apps/kanana-2-v-decide-3b

multimodalart published a Space about 8 hours ago

hugging-apps/speridlabs-idol-turbo

View all activity

hugging-apps 's Spaces 818

BluePixel-Turbo

Native 4K instruction-based image editing in 4 steps

Kanana-2-v-decide-3b

Typed decision questions over text, JSON, or images

Idol Turbo

One image to a 3D object in 5 guidance-free distilled steps

GLiDE-0.4B Decision Model

Typed questions in, calibrated probabilities out

THX-02

Thinking decision model with calibrated probabilities

GenFirst Text-to-Image

GenFirst EiT MMDiT-XL/2 512px text-to-image

Hima-ASR

Indic speech to text and speech to decisions

Taraneh-WLarge Persian ASR

Persian speech-to-text with word-level time alignment

Klein-TTS X1.5 Flash Lite

0.4M-param TTS in English, French and Italian

VidDub

Two-step audio-driven video dubbing from replacement speech

Qwenputer CHIP-8

Qwen3.5-4B with a CHIP-8 computer compiled into its weights

SphereFlow

Impute missing MRI/CT modalities with SphereFlow

VidDub

Two-step video dubbing — re-sync lips to new speech

TrajLoc

Draw per-object paths, animate an image (CogVideoX)

LTF · AI-Generated Image Detector

Detect AI-generated images with hierarchical MIL attention

Semantic Transport Generation

One-step ImageNet-256 class-conditional image generation

DaFeiYu RVC v2 40k

RVC v2 voice conversion into the DaFeiYu voice

Torchcast Decision 4B

Typed decisions with probabilities in one forward pass

P-JiT 21K

Pixel-space text-to-image DiT trained for $21K

PLaMo 3 Translate 0.8B

Translation across 53 languages with a 0.8B specialized LLM

iota-decide-4b

Typed decisions: state in, calibrated probabilities out

AuroraIMG2-100M

100M-param from-scratch flow-matching t2i model, 256x256

PixelGen

1,257 hand-written params, 0 training steps

History Forcing Long-Horizon Video

Few-step autoregressive long-horizon text-to-video