LoL: Longer than Longer, Scaling Video Generation to Hour Paper âĒ 2601.16914 âĒ Published Jan 23 âĒ 22
Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset Paper âĒ 2510.15742 âĒ Published Oct 17, 2025 âĒ 51
thedeoxen/refcontrol-flux-kontext-reference-pose-lora Image-to-Image âĒ Updated Aug 27, 2025 âĒ âĒ 61
view article Article One-Sentence Image Matting! DiffSynth Open Sources Text-Guided Image Layer Separation Model Jan 14 âĒ 3
Running on Zero Agents Featured 500 Qwen Image Layered ð 500 Decompose images into editable layers and download them
TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs Paper âĒ 2512.14698 âĒ Published Dec 16, 2025 âĒ 21
Running on Zero Agents 3 MagicQuillV2 ðŠķ 3 Generate edited images with precise control over color, edges, and prompts
Running on Zero Agents 3 MagicQuillV2 ðŠķ 3 Generate edited images with precise control over color, edges, and prompts
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation Paper âĒ 2512.04678 âĒ Published Dec 4, 2025 âĒ 42