FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing
cs.CV, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/black-forest-labs/flux
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- PaddleOCR 3.0 Technical Report
- Recognition-Synergistic Scene Text Editing
- FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
- FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing
- Flow Matching for Generative Modeling
- UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation
- PRIM: Towards Practical In-Image Multilingual Machine Translation
- Taming Rectified Flow for Inversion and Editing
- Qwen-Image Technical Report
- Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering
- TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
- All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
- PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
- LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling
- KV-Edit: Training-Free Image Editing for Precise Background Preservation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs