🏗️ Building on HF

Apolinário from multimodal AI art PRO

multimodalart

huggingface

·

https://multimodal.art

AI & ML interests

ML + art and creativity

Recent Activity

published a Space 12 minutes ago

hugging-apps/medsam3-v1

updated a Space 25 minutes ago

hugging-apps/medsam3-v1

new activity about 1 hour ago

Prior-Labs/tabpfn_3_5:Demo for this model on Spaces

View all activity

Organizations

multimodalart 's Spaces 337

VQGAN + CLIP

Watch an image form from noise, and keep the whole descent.

MiniMax H3

Video generation with a synchronized soundtrack

MiniMax-H3 Reference

Unquantized MiniMax-H3 from image, audio, video refs

MiniMax-H3 Reference

Unquantized MiniMax-H3 from image, audio, video refs

Real-Time Text-to-Image SDXL Lightning

Real-Time Image Generation with SDXL Lightning

Krea 2 LoRA Trainer

Train Krea 2 LoRAs on your images via HF Jobs

Blue Tigers

Generate personalized videos and rate them to refine recommendations

The Other Tiger

Generate images you like by rating displayed pictures

Liquid Image to JSON

Turn any image into structured JSON with LFM2.5-VL Extract

Unique3D

Create a 1M faces 3D colored model from an image!

Unique3D

Create a 1M faces 3D colored model from an image!

Zonos

Generate expressive speech from text

MinerU Document Extraction Tools

Easy converting PDF and Office docs into Markdown and JSON

Unique3D

Create a 1M faces 3D colored model from an image!

MelodyFlow

Generate short music clips from text and optional melody

T2V Turbo V2

Efficient T2V generation

Zonos

Generate expressive speech audio from text with voice cloning

Fun-CosyVoice3-0.5B

Generate speech that mimics a given voice sample

MusicGen

MassivelyMultilingualTTS

Generate speech from text in 7000 languages

Face to All

AI filter for your portraits

Qwen Image Edit Light Migration

Apply the lighting from one image to another image

FLUX.2 [dev] Turbo

Faster 8 step turbo FLUX.2 by fal

FireRed Image Edit 1.0 Fast

FireRed-Image-Edit × Qwen-Image-Edit-Rapid (Transformers)