Lance
🎬
1
Generate, edit, and understand images and videos with Lance!
Spaces HF ML Demo 2026 - GPU Needs
-
-
LocateAnything
💬8Detect and annotate objects in images or videos
-
Qwen Image Edit + Loras built-in
👀83Qwen image edit with 🔞 loras
-
Cosmos3 Nano
🌌13Create videos (and images) from text prompts
-
LongCat-Video-Avatar 1.5
🎤8Audio-driven talking-head video generation (Meituan LongCat)
-
LFM2.5 8B A1B
🌖3Chat with an AI assistant using customizable prompts
-
MiniCPM V 4.6
👁Chat with AI using text, images, and videos
-
ZAYA1-8B
⚡24Chat with a powerful reasoning assistant
-
Bonsai Image GPU
🎨11Run Bonsai-Image-4B models on GPU
-
VibeThinker 3B
😻8Generate detailed answers with step‑by‑step reasoning
-
LTX 2.3 10Eros Image-to-Video
🎬3ltx 2.3 improved image-to-video with 10eros & native audio
-
TeleStyleV2
🚀43Edit images with style transfer using content and style references
-
LTX-2.3 Ingredients LoRA (Fast)
⚡32Fast reference-sheet to video with LTX-2.3 IC-LoRA
-
Agentic Space Factory
🏭5Build, inspect, validate Gradio Spaces from model cards.
-
MiniMax H3
🎬119Video generation with a synchronized soundtrack
-
Unlimited OCR
🏆52Extract text from images and PDFs
-
Audio8 TTS Preview 0.6B
🚀58Clone a voice and generate speech in multiple languages
-
Qwen 3.5 HF Demo
🤗43Demo of the Qwen 3.5 Multimodal Model
-
Lightricks/LTX-2.5
Image-to-Video • Updated • 1.72M • 7.16k -
MiniMax Music 3 Studio
🎵354Generate custom music tracks from text captions and lyrics
-
Qwen-Image-Edit-2511-LoRAs-Fast
🎃2.78kDemo of the Collection of Qwen Image Edit LoRAs
-
MiniMax H3 Turbo LoRA
🎬510Video generation with a synchronized soundtrack
-
LTX 2.5
⚡27Generate videos from text prompts (optional image)
-
LTX-2.5 Pixel Video Upscaler
🎞5Creative 2x video upscaling with LTX-2.5
-
Qwen3.8 27B Object Detection
⚗32Unleash the Power of Visual Grounding
-
AI Creative Studio
🎵2Chat with powerful AI models and create audio/video
-
Kimi K3 GGUF Demo
🦥2Chat + Unsloth GGUF guide for Kimi K3
-
SenseNova-U1.5-8B-MoT
🎨135Unified text-to-image and image editing model
-
JoyAI Video Edit (Live)
🎬60Real-time webcam video editing (ZeroGPU)
-
OpenAjaj
🤖1Verify you're human with a sliding puzzle captcha
-
FireRedAudio
🔥35Voice cloning, voice design, speech editing and ASR
-
Video-ORA-9B
🎯17Explore all seven Video-ORA task families
-
LTX Ripple
🎬45Edit one frame, ripple the change through the whole video
-
Krea 2 Identity Edit
🧬251Identity-preserving instruction image editing on Krea 2
-
SoL-Refiner LTX-2.5 for MiniMax-H3
✨268One-step 1080p refinement of MiniMax-H3 videos
-
LTX-2.5
🎬26Multi-task image generator with dynamic, chainable workflows
-
Viggle-Animate
🕺83Put the person from a still into a driving video, in 4 steps
-
Scribble Board Fast
🖌3A fast digital sketchboard.
-
OpenCaption-4B-VL-SFT
📝5Dense fine-grained image captioning with Qwen3-VL-4B
-
YuE2-3B Music Generator
🎵209Generate songs and covers from style prompts and lyrics.
-
StepAudio 3 Music Studio
🎵203Create songs, arrange vocals, and remix music with StepFun
-
Marigold V2
🌼125Depth, surface normals, and albedo from a single image
-
AuK
🎙127Unified speech generation and editing with AuK
-
Qwen3.8 27B
💻91Chat with Qwen3.8-27B using this hosted demo.
-
Qwen3.8 27B
💻1Generate AI-powered text responses from your prompts
-
Respite API
🤖Generate music or sound effects from a text prompt
-
MiniMax H3 Turbo LoRA
🎬1.37kVideo generation with a synchronized soundtrack
-
MuLaCover
🎤42AI cover songs from reference audio, lyrics and style
-
Meridian
🧭62Generate a new camera view from your video or image
-
Qwen-Image-2.1 Object Remover Bbox Turbo
🗑11Box an object and let Qwen-Image-2.1 erase it.
-
Qwen-Image-2.1-LoRAs-PnP
🌖35Collection of Qwen-Image-2.1 LoRAs — Plug and Play
-
Laya Demo
🎯272Fast System 1 decisions with calibrated probabilities
-
Qwen-Image-2.1
🎨407Generate or edit images from text and photos
-
Viggle Turbo for Qwen-Image-2.1
⚡2416-step Qwen-Image-2.1, T2I + editing, vs-base comparison
-
Qwen-Image 2.1 Move
🎁56Move & resize objects with Qwen-Image 2.1 turbo, no LoRA
-
PDMD 4-NFE / 2-NFE MiniMax-H3
⚡24/2-step text- & image-to-video+audio, PDMD on MiniMax-H3
-
Tr@nsf0rmation_style MiniMax-H3 LoRA
🦋1Morph one picture into another with MiniMax-H3
-
Qwen-Image 2.1 Detail Enhancer LoRA
🔍2Detail enhancement & 2K upscaling for Qwen-Image 2.1
-
MiniMax-H3 360° Equirectangular LoRA
🌐1Text-to-360° video with native audio on MiniMax-H3
-
SoL-Refiner LTX-2.5 for MiniMax-H3
✨2One-step 1080p refinement of MiniMax-H3 videos
-
Turbo8 - 8-step Qwen-Image-2.1
🚀88-step, no-CFG generation and editing with the Turbo8 LoRA
-
Iris-3B
👁9Pixel-space generation & general vision learner