Krea 2 Identity Edit
🧬
190
Identity-preserving instruction image editing on Krea 2
Community Spaces
Apps started here then claimed by the 🐐 authors
-
-
CharacterSheet LoRA Demo
🧑146Multi-view character sheet from one image (FLUX.2 LoRA)
-
Mage-Flow
🎨126Efficient native-resolution image generation and editing
-
Mage-VL
🎞103Codec-native video & image understanding with Mage-VL 4B
-
Krea 2 Outpaint
🖼101Extend images into larger canvases with Krea 2 outpaint
-
ABot-World Interactive
🌍94Live interactive world rollout from an image
-
Krea 2 Turbo BBox
🧩52Layout-controlled comics with a draggable bbox canvas
-
LTX-Best-Face-ID
🎬48Distilled LTX-2.3 identity video from a reference photo
-
Nemotron-Labs-Audex
🎧42Unified audio-text intelligence
-
CADENA Stepwise CAD
📐42Turn a 3D mesh into a parametric CadQuery program
-
VibeVoice ASR BitNet
🎙37Multilingual CPU-only ASR with a 1.58-bit BitNet decoder
-
MOSS-VL-Realtime
👁30Realtime VLM for image and video understanding
-
A.X K2 Raon-Speech 21B-A3B
🗣23Bilingual EN/KO speech LM - transcribe, ask, and speak
-
SpotSound Temporal Grounding
🔍23Find when a described sound happens in a recording
-
SenseNova U1 Infographic V3
📊17Infographic generation & editing with SenseNova-U1 V3
-
CrisperWhisper 2.0 Controllable ASR
🎙18Verbatim + intended transcripts with word-level timing
-
StuPASE Speech Enhancement
🎙17Studio-quality generative speech enhancement
-
WordVoice Word-Level Controllable TTS
🗣14Zero-shot TTS with explicit word-level prosody control
-
Aerial Imagery Object Detection
🚁13Aerial object detection - YOLO Models
-
LTX 2.3 Pixel Spatial Upscaler
🎞10Generative 4x video upscaling with LTX-2.3 IC-LoRA
-
QueenVIS Video Instance Segmentation
👑10Segment and track object instances in video with QueenVIS
-
Krea-2 Depth ControlNet
🏔8Depth-controlled image generation with Krea-2 Turbo
-
LTX CrossView-Prompt - Video Camera Control by Prompt
🎥8Re-render a video from a new camera angle via IC-LoRA
-
LTX-2.3 Clean Plate (Remove People from Video)
🎬8Remove people & vehicles from video, keep the background
-
MonkeyOCRv2 Document Parser
📄8Parse document images into structured Markdown
-
Glint-2 Effort Explorer
🔄71.06M-param pure-loop transformer with six effort levels
-
Krea 2 Style Reference
🎨7Style-guided image generation with Krea 2 Turbo
-
ClinFusion Medical VLM
🏥8ClinFusion medical multimodal LLM for 2D images
-
MiniMax-H3 Spatial Physics LoRA
🎬7Spatial physics video generation with MiniMax-H3 LoRA
-
Flux2-Klein-9B-True-V3 Edit
🎨6FLUX.2 Klein 9B fine-tune for image generation and editing
-
Krea 2 Turbo HD
🎨6Krea 2 Turbo HD text-to-image with enhanced VAE
-
HPD-Parsing
📄6Hierarchical parallel document parsing with a 1B VLM
-
MiLMMT-46 Translation (12B)
🌍6Multilingual translation across 46 languages with MiLMMT
-
SCoPE Camera Controlled Video
🎥6Steer a 3D camera path through any still image
-
Reproduction: Matroid Algorithms Under Size-Sensitive Independence Oracles
🔗5Native size-sensitive matroid audit
-
AudioRubrics
🎧5Audio reasoning with evolving rubric rewards
-
NK2E Krea 2 Image Editor
🎨4Edit images or generate from Canny edges with NK2E on Krea 2
-
ViT-Up Feature Upsampler
🔼4DINOv3 feature upsampling with ViT-Up
-
Supra-A2A-Nano-Exp
🌐4Tiny any-to-any multimodal GPT (text + image) prototype demo
-
LightOn-rerank-PW
✨4LightOn multimodal document reranker with pointwise scoring
-
LTX-2.3 Product Ad Style
🎬4Cinematic product commercial style video LoRA for LTX-2.3
-
GLiNER2 Guardrails PII Multi
🔒4Multilingual PII detection & LLM safety moderation
-
Jolia
🫁4Zero-shot CT findings with the Jolia 3D CT foundation model
-
SupraElegans-500K Explorer
🪱4Watch a 574K-param non-Transformer LM think
-
Play Charles the Chess Bot
♟4Play chess against a 32.5M-param search-free policy
-
Tafsut Forecast
📈6Zero-shot probabilistic time-series forecasting
-
Semancer 12B
🔮3Occult philosophy chat LLM fine-tuned on Gemma 4 12B
-
Arithmetic-SLM
🧮3Tiny 31.7M SLM that solves arithmetic expressions
-
Krea 2 HDR LoRA (LogC4)
🌇3Generate scene-linear HDR images with Krea 2 + LogC4 LoRA
-
Bernini-R-S2V Talking Head
🎙3Speech-driven talking-head video (Bernini-R S2V, Wan2.2)
-
Scrappy Voice TTS
🗣3Four voices in one 10M-param CPU model, with blending
-
Jina Reranker v3.5 Demo
📊3Listwise document reranker with jina-reranker-v3.5
-
Inline Skin LoRA — Krea 2
🎨3Photorealistic skin-texture LoRA for Krea 2 Turbo
-
MobileWan T2V
🎬3MobileWan text-to-video generation (Qualcomm AI Research)
-
Audio8-ASR-0.1B
🎙3Compact multilingual ASR model (324M params)
-
OpenCaption-4B-VL-SFT
📝3Dense fine-grained image captioning with Qwen3-VL-4B
-
Aero Realtime 4B
📺3Proactive real-time commentary on audio-video streams
-
OpenDDE Structure Prediction
🧬3Predict 3D protein structures with OpenDDE
-
Mr. Balance
🍽3An RL plate that balances 21 objects in MuJoCo
-
DomainShuttle Subject Video
🎬2Subject-driven text-to-video from reference images (Wan2.2)
-
Arabic Speech Tashkeel
🕌2Arabic speech to fully-diacritized text (tashkeel)
-
SAGE Visual Place Recognition
🗺2SAGE retrieves matching place images from a gallery
-
MolParser-Mobile
🧪2Convert molecular structure images into E-SMILES strings
-
AlienLM
🛸2AlienLM privacy layer for black-box LLMs
-
Translate-15L
🌍2Compact 60M T5 translator for 15 languages
-
UniAR
🎨2Unified AR model for image understanding & generation
-
ASASR Super-Resolution
🔍2Faithful x4 image super-resolution via FLUX.1-dev dual-LoRA
-
SauerkrautLM-LFM2.5-GLiNER
🥬2Zero-shot multilingual NER with GLiNER on LFM2.5-350M
-
Tiron Meeting Transcriber
🎙2Multi-speaker meeting transcription with diarization
-
WATERec WordArt Recognition
🎨2Recognize text from WordArt / artistic scene text images
-
LTX-2.3 Relight (Video Relighting IC-LoRA)
💡2Relight exterior video clips with a light-direction ball
-
MOSS-VL-Instruct-0708
🧠2Image and video understanding with MOSS-VL multimodal model
-
Histoformer All-Weather Restoration
🌧2Remove adverse weather effects (Histoformer, ECCV 2024)
-
Miril-DroneVLM-2B-2 Demo
🚀1Speak to a drone using an image, video, text, or voice.
-
EpistemeAI Reasoning-Medical-27B
🏥1Medical reasoning VLM based on Qwen3.6-27B
-
OmniAgent-RL
🎬1Agentic video understanding with active perception loop
-
BioMatrix-4B-SFT
🧬1Multimodal bio foundation model for molecules & proteins
-
MolmoMotion
🎯1Forecast 3D point trajectories from video and language
-
LabVLA
🧪1VLA model for scientific laboratory robotics
-
DI2FIX Enhancer
✨1Distractor-free 2D enhancer for radiance field renderings
-
DoctoBERT Fill-Mask
🩺1Fill-mask demo for a French medical ModernBERT
-
Wan2.2 IS2V Talking Head
🗣1Speech-driven lip-sync on Wan 2.2 image-to-video
-
WSA-Base Robot Control
🤖13D-centric world-spatial-action robot policy demo
-
JoyAI-Echo x LTX-2.3 Multi-Shot Video
🎬1Multi-shot narrated video with cross-shot memory
-
JoyAI Image Edit Plus
🎨1Multi-image instruction-guided image editing
-
SHINE Context to LoRA
🔆1Encode a context into a LoRA and chat with Qwen3-8B
-
Hardware Blueprint Generator
🔧1Turn hardware ideas into structured JSON blueprints
-
LTX-2.3 Cameraman v2 — Camera Motion Transfer
🎬1Replicate camera motion from a reference video via IC-LoRA
-
Ava Persian TTS
🗣1Persian TTS demo using Ava-82M (Kokoro-based)
-
Lumma 0.6B Tool Playground
🛠1Define JSON tools and watch Lumma-0.6B generate tool calls
-
grug-v2-9b
🐦1Multimodal reasoning VLM with Grug-style thinking
-
MimiLens Watermark Detector
🔍1Detect watermarks, signatures, and artifacts in images
-
BarunAction-35M
🧭1Proposal-only typed personal actions with a 35M-param model.
-
ShotPlan Cinematic T2V
🎬1Multi-shot cinematic text-to-video generation
-
MBA Business Ideation Agent
💡1Generate market-grounded business ideas from images with MBA
-
MiLMMT-46 Translation (4B)
🌍1Multilingual translation across 46 languages with MiLMMT
-
LATO.2
🔺1Rebuild any 3D mesh as a clean artist-style mesh
-
VideoSearch-R1
🎬1Video verification & temporal grounding with VideoSearch-R1
-
UNCHA Hyperbolic VLM
🔮Hyperbolic vision-language zero-shot classification
-
Baberu OCR
📖Multilingual manga speech-bubble OCR (JA/ZH/EN)
-
MeanFlowNFT Few-Step Generation
⚡4-step RL text-to-image with MeanFlowNFT on SD3.5-Medium
-
LocalSubs EN-ZH-TW Subtitle Translation
💬EN subtitle cues to Taiwan Traditional Chinese (0.6B model).
-
HiMoE-VLA Action Prediction
🤖Predict robot action chunks from an image + instruction
-
EM3M-Gen
🔬Generate electron micrographs from text prompts
-
Temporal-MoEs-RoBERTa Emotional State-Change Forecaster
🧭Forecast Valence & Arousal state change from posts
-
Graph-PrefLexOR Scientific Reasoning
🧠Graph-native LLM scientific reasoning with graph viz
-
MOSS-TTS-PNY
🎙Speaker-conditioned TTS with emotion & energy control
-
MrFlow Fast Diffusion
⚡MrFlow training-free diffusion acceleration demo
-
LoomVideo
🎬Unified multimodal video generation and editing (5B)
-
InterleaveThinker
🤖Multi-agent interleaved text-image generation pipeline
-
Perceive-to-Reason
👁P2R fine-grained visual reasoning with Qwen3-VL
-
TASKER Keyframe Extractor
🔍VLM-guided tree-search keyframe extraction from videos
-
HOMA
🎬Human-object interaction video from image+audio+text
-
AffectFlow-DINO
😊Facial affect estimation with uncertainty via rectified flow
-
TimEE In-Context Time Series Classification
📈Classify time series in-context with TimEE foundation model
-
LTX CrossView Warp
🎥Novel camera viewpoint from a video via depth-warp IC-LoRA
-
EchoVLM Ultrasound Demo
🩺Ultrasound image understanding VLM with MoE architecture
-
SamplingTAR Defense
🛡Training-free typographic attack defense for CLIP
-
LongE2V Event-Video Reconstruction
🎬Reconstruct video from event-camera voxel grids via LongE2V
-
Lung Ultrasound Video Classification
🫁4-class lung ultrasound video classifier with attention
-
DAV-Det AIGC Audio-Video Detector
🎥Detect AI-generated audio-visual content (DAV-Det)
-
SpatialAxiom-9B
🧠Spatial reasoning VLM for 3D relations and perspective
-
PEC Breast MRI VCE
🩻Synthesize contrast-enhanced breast MRI from pre-contrast
-
FACT World-Action Model
🤖Counterfactual robot futures from a world-action model
-
MiLMMT-46 Translation (1B)
🌍Multilingual translation across 46 languages with MiLMMT
-
Korean Toxicity Deobfuscation KOTOX
🧼Deobfuscate and detoxify Korean text with KOTOX
-
LULA-1.1 Protein-Ligand Binding Scorer
🧬Sequence-only protein-ligand binding scorer (LULA-1.1)