WeLM-Image: A Unified Image Generation Model towards Visual Intelligence
cs.CV, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/black-forest-labs/flux
Terminology
Sources
- TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
- Qwen-Image Technical Report
- Step1X-Edit: A Practical Framework for General Image Editing
- HunyuanImage 3.0 Technical Report
- SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
- Emerging Properties in Unified Multimodal Pretraining
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
- DanceOPD: On-Policy Generative Field Distillation
- Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
- Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance
- Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
- Classifier-Free Diffusion Guidance
- Kimi-VL Technical Report
- NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
- Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- DeepSeek-V3 Technical Report
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
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