FLUX 3 Video update ranks #2 in Text-to-Video Arena, just 16 pts behind leader
bfl_ai · x · 2026-08-12
Black Forest Labs' updated FLUX 3 Video ranks #2 in the LMSYS Text-to-Video Arena with 1496 points, just 16 points behind the leader Gemini Omni Flash (1512). The model supports native audio, text-to-video, image-to-video with multiple frames, video continuation, and multilingual dialogue, plus a draft mode for faster exploration at lower cost. It generates up to 20 seconds at 1080p natively, and will be available via API and tools, with 2K, 4K, and open weights coming soon.
Related event: Updated FLUX 3 Video Ranks Second Globally and Offers Free Access(2 posts)→
More from Multimodal
- ComfyUI Workflow: Krea2 and Qwen3-VL for Reference Style Inpainting — TBG______ · 2026-08-12
- Benchmarking Minimax-h3-Turbo LoRA: Generates 480p Video in 56s with 4 Steps — LegacyV1 · 2026-08-12
- IndexTTS 2.5 Released: Open-Source Text-to-Speech Model Upgraded — Internal_Answer_6866 · 2026-08-12
- Seedance 2.5 Prompt Library: How to Generate Realistic Smartphone Videos — SimplyAnnisa · 2026-08-12
- AI Music Generation Case: Terafab Releases Space-Themed Track — danshipper · 2026-08-12
- Low VRAM Friendly: Testing Minimax H3 Video Upscaling on 12GB GPU — rm_rf_all_files · 2026-08-12