Black Forest Labs 发布开源权重图像模型 FLUX 3 Image Klein，可在 8 GB 显存消费级 GPU 上运行
Black Forest Labs' open-weights image model FLUX 3 Image Klein runs on consumer GPUs with just 8 GB of VRAM
- 1Black Forest Labs 发布 5.6 十亿参数开源权重图像模型 FLUX 3 Image Klein
- 2官方称内测中 Elo 评分在开源模型里最高，超越闭源竞品 Ideogram V4.5
- 3INT8 版本以 8 GB 显存在消费级 GPU 运行，RTX 4070 上不到 9 秒生成图像
- 4权重对年收入低于 $5 million 的公司免费商用，API 每 1,000 张 $0.009
开源权重图像模型能力被官方宣称超越部分闭源对手，运行门槛降到单张 8 GB 消费级 GPU，企业图像生产的成本结构需要重算。
- 影响：年收入低于 $5 million 的公司可免费商用权重，图像素材成本有望压缩到硬件和电费；有 8 GB 显存设备的团队可先尝试本地部署，减少 API 支出；LoRA 微调从第一天就可用，自制风格化素材的门槛降低。
- 参考：可考虑挑一个批量图像素材场景做对比测试，记录与现有 API 采购的质量和耗时差异；值得先盘点手头 GPU 是否达到 8 GB 显存，并确认公司年收入是否落在免费授权范围内。
- 依据：超越 Ideogram V4.5 与 FLUX.2 [pro] 的对比来自 Black Forest Labs 内部测试，暂无独立验证；8 GB 显存运行、授权条款与 API 定价均为官方发布信息。
Oct 15, 2026
Black Forest Labs has released FLUX 3 Image Klein, a 5.6-billion-parameter open-weights model for text-to-image generation, image editing, and generation with up to ten reference images. It supports native 4K output, pixel-accurate editing, and bounding boxes for element placement. Black Forest Labs says it scores the highest Elo ratings among all open models in internal testing, beating closed competitors Ideogram V4.5 and even BFL's own FLUX.2 [pro]. It gains 91 Elo points over FLUX.2 [klein] with 38 percent fewer parameters than that model's 9 billion.
An INT8 build lets it run on NVIDIA GPUs with just 8 GB of VRAM, generating an image in under 9 seconds on an RTX 4070. The weights ship under the FLUX Kommunity License, free for commercial use by companies making under $5 million annually. The model is also available through the BFL API at $0.009 per 1,000 images, as a Playground, on Hugging Face Spaces, and locally via ComfyUI and Diffusers. LoRA training works from day one through Ostris AI Toolkit and NVIDIA NeMo AutoModel.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
来源：The Decoder：AI News · the-decoder.com