[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-flux-3-image-klein-open-weights":3,"topics-all":38,"news-related-b88d9e4c-1450-4349-a3cd-c2f8c0ce50eb":57},{"id":4,"title":5,"summary":6,"content":7,"original_url":8,"source_id":9,"tags":10,"translations":24,"news_slug":31,"published_at":32,"created_at":33,"modified_at":34,"is_published":35,"publish_type":36,"image_url":14,"view_count":37},"b88d9e4c-1450-4349-a3cd-c2f8c0ce50eb","FLUX 3 Klein 开源:5.6B,8GB 显存能跑","Black Forest Labs 开放 5.6B 生图模型 FLUX 3 Image Klein 权重,支持文生图、编辑与最多 10 张参考图组合,继承 4K 生成与边界框控制。INT8 版最低 8GB 显存可跑,蒸馏版 RTX 5090 约 4 秒出 1MP 图,官方内部评测开放权重排名第一。","10 月 15 日,Black Forest Labs(BFL)放出 FLUX 3 家族的第二个开放权重模型:FLUX 3 Image Klein。继 7B 机器人控制模型 FLUX 3 Action 之后,这次轮到图像。5.6B 参数、消费级显卡可跑、生成与编辑同一模型——BFL 继续把「旗舰质量 + 本地部署」往低配硬件压。\n\n## 参数不大,分工明确\n\n5.6B 指图像 transformer 本体;文本编码器另算,用的是阿里的 Qwen3-VL-4B-Instruct(Hugging Face 模型卡注明)。模型接收 prompt 加最多 10 张参考图,输出一张图:文生图、单参考编辑、多参考组合走同一套权重。\n\n发布 base 与蒸馏版两个 checkpoint:前者给微调和 LoRA 训练,后者主打低延迟,另与 NVIDIA 合作提供 FP8、INT8、NVFP4 量化构建。生成器权重 BF16 下 11.2 GB、FP8 下 5.6 GB;INT8 版最低 8GB 显存即可跑 ComfyUI 或 Diffusers。蒸馏版在 RTX 5090 上约 4 秒出一张 1MP 图,RTX 4070 上不到 9 秒。\n\n## 厂商评测:小个子第一\n\nBFL 内部评测里,Klein 在文生图、多参考生成、图像编辑三项排开放权重第一,高于对比中的闭源模型 Ideogram V4.5 与 FLUX.2 [pro]。它还是对比阵容里最小的:5.6B 对 Qwen-Image 2.1 的 7B、Krea 2 的 12.9B;与上一代 FLUX.2 [klein] 9B 相比,文生图 Elo 高 91 分、编辑高 70 分,参数少 38%。这些排名全部来自厂商评测,尚无第三方复测;但「更少参数更高分」与 FLUX 3 把图像、视频、音频信号共享进预训练的思路一致。\n\n它继承 FLUX 3 Image 的核心能力:4K 原生生成、pixel-perfect 编辑、边界框控制。\n\n## 生态与授权:门槛在商业侧\n\nDay-one 支持 ComfyUI、Diffusers、TensorRT-LLM、SGLang、vLLM-Omni;LoRA 训练有 AI Toolkit 与 NeMo AutoModel 配方。授权是 FLUX Kommunity License:年收入 500 万美元以下免费商用;更大的组织需走自托管授权或 API,蒸馏版 1K 图 0.009 美元起。安全侧经内部红队与外部伙伴 Cinder 评估,BFL 称漏洞显著少于其他主流开放权重模型。\n\n## 所以呢\n\n看点不在刷分,而在本地图像编辑门槛又低一档:8GB 显存覆盖大量在售笔记本显卡,4 秒出图进入交互区间;叠加 Qwen3-VL 编码器,中文 prompt 亲和性值得期待。真正要读细的是 500 万美元营收分界线:对个人和中小团队是免费午餐,对企业级自托管就是谈判桌。下一个问题:4K 原生加 10 参考图的组合,会不会把本地工作流从「生成」推向「编辑」?\n\n引用:[BFL 官方发布页](https:\u002F\u002Fbfl.ai\u002Fblog\u002Fflux-3-image-klein)、[Hugging Face 模型卡](https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002Fflux-3-image-klein),独立报道见 [VentureBeat](https:\u002F\u002Fventurebeat.com\u002Ftechnology\u002Fblack-forest-labs-opens-flux-3-image-klein-weights-with-free-commercial-use-limited-to-smaller-businesses)。","https:\u002F\u002Fbfl.ai\u002Fblog\u002Fflux-3-image-klein","12897aab-bc2f-4ce3-9a8d-8be683b675ef",[11,15,18,21],{"id":12,"name":13,"slug":13,"description":14,"color":14},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":16,"name":17,"slug":17,"description":14,"color":14},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":19,"name":20,"slug":20,"description":14,"color":14},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",{"id":22,"name":23,"slug":23,"description":14,"color":14},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image",[25],{"id":26,"lang":27,"title":28,"summary":29,"content":30},"3e517942-35f5-4704-9f40-83f3e920352e","en","FLUX 3 Klein Open Weights: 5.6B Image Model Runs on 8GB VRAM","BFL open-sources FLUX 3 Image Klein, a 5.6B text-to-image and editing model running on 8GB VRAM, first in BFL's internal open-weights rankings.","On October 15, Black Forest Labs (BFL) shipped the second open-weights release from its FLUX 3 family: FLUX 3 Image Klein. The first was FLUX 3 Action, a 7B model for robot control; this one is for images. 5.6B parameters, consumer-GPU friendly, generation and editing in a single model — BFL keeps pushing the \"flagship quality, local deployment\" line further down the hardware stack.\n\n## Small transformer, clear division of labor\n\nThe 5.6B count refers to the image transformer itself; the text encoder is separate — Alibaba's Qwen3-VL-4B-Instruct, per the Hugging Face model card. The model takes a prompt plus up to 10 reference images and returns one image: text-to-image, single-reference edits and multi-reference compositions all run through the same weights.\n\nTwo checkpoints shipped: a base model for fine-tuning and LoRA training, and a step-distilled model for low latency. Quantization comes in FP8, INT8 and NVFP4 builds developed with NVIDIA. Generator weights are 11.2 GB in BF16 and 5.6 GB in FP8; with the INT8 build the model runs on RTX GPUs with as little as 8GB of VRAM via ComfyUI or Diffusers. On speed, the distilled model with INT8 generates a 1MP image in about 4 seconds on an RTX 5090 and under 9 seconds on an RTX 4070; on GB300, NVFP4 comes in under 0.6 seconds.\n\n## Vendor evals: the small one ranks first\n\nIn BFL's internal evaluations, Klein ranks first among open-weights models in text-to-image, multi-reference generation and image editing, and rates above the closed models in the comparison, Ideogram V4.5 and FLUX.2 [pro]. It is the smallest model in that comparison: 5.6B against 7B for Qwen-Image 2.1 and 12.9B for Krea 2. Versus the previous FLUX.2 [klein] 9B, it gains 91 Elo in text-to-image and 70 in editing, with 38% fewer parameters. Caveat: these rankings all come from the vendor's own evals, with no independent third-party replication yet — but the \"fewer parameters, higher score\" direction is consistent with FLUX 3's pretraining recipe, which shares signals across images (spatial detail), video (motion and physical dynamics) and audio (events and interactions).\n\nKlein also inherits FLUX 3 Image's core capabilities: native 4K generation, pixel-perfect editing, and bounding boxes that control where elements land or confine edits to a defined area.\n\n## Ecosystem and license: the gate is commercial\n\nDay-one support is broad: ComfyUI, Diffusers, TensorRT-LLM, SGLang Diffusion and vLLM-Omni; LoRA training via Ostris's AI Toolkit and recipes in NVIDIA NeMo AutoModel. The license is the FLUX Kommunity License: free commercial use for individuals and companies under 5 million US dollars in annual revenue, plus research and non-commercial use; larger organizations need self-hosting licenses or the API. API pricing for the distilled model starts at 0.009 US dollars per 1K images. On safety, the checkpoints were red-teamed internally and evaluated by external partner Cinder; BFL says they show substantially fewer vulnerabilities than other popular open-weights models.\n\n## So what\n\nThe story here is not leaderboard points but the dropping barrier to local image editing: 8GB of VRAM covers a large slice of laptops on sale today, and a 4-second distilled generation enters interactive territory. Add Qwen3-VL as the text encoder and Chinese-prompt friendliness is worth watching. The fine print that matters is the revenue line — a free lunch for individuals and small teams, a negotiation for enterprise self-hosting. The next question: will native 4K plus 10 reference images push local workflows from generation all the way to editing?\n\nSources: the [BFL release post](https:\u002F\u002Fbfl.ai\u002Fblog\u002Fflux-3-image-klein) and [Hugging Face model card](https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002Fflux-3-image-klein); independent coverage at [VentureBeat](https:\u002F\u002Fventurebeat.com\u002Ftechnology\u002Fblack-forest-labs-opens-flux-3-image-klein-weights-with-free-commercial-use-limited-to-smaller-businesses).","flux-3-image-klein-open-weights","2026-10-17T13:20:00Z","2026-10-17T13:10:47.851121Z","2026-10-17T13:10:47.851132Z",true,"agent",238,[39,48],{"slug":40,"tag_slug":40,"title_zh":41,"title_en":42,"intro_zh":43,"intro_en":44,"id":45,"is_active":35,"created_at":46,"modified_at":47},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":49,"tag_slug":49,"title_zh":50,"title_en":51,"intro_zh":52,"intro_en":53,"id":54,"is_active":35,"created_at":55,"modified_at":56},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":58},[59,64,69,74,79,84],{"id":60,"title":61,"news_slug":62,"published_at":63},"c480d2d0-9156-4aa7-826f-fba2f252b6b7","蚂蚁开源 LLaDA-Image:6B 参数生成编辑一体,Turbo 版 4 步出图","ant-llada-image-open-generation-editing","2026-09-04T13:09:21+00:00",{"id":65,"title":66,"news_slug":67,"published_at":68},"095917eb-02ae-4fd2-a1cb-17d0805442ee","微软 Mage-Flow 用 4B 跑赢 32B：原生分辨率 + 三件套协同设计把生成编辑都塞回单卡","microsoft-mage-flow-4b","2026-07-23T03:30:00+00:00",{"id":70,"title":71,"news_slug":72,"published_at":73},"f7287cac-6643-4f4a-8cbd-2b281d2d4d46","Krea 2 开源双发：12B DiT 把「2 秒出图」做进主流程，蒸馏后 8 步直出 2K","krea-2-12b-dit-2-second-turbo","2026-06-25T10:30:00+00:00",{"id":75,"title":76,"news_slug":77,"published_at":78},"72ee21ea-8a91-4dd3-88fa-f605551ff9ce","Qwen-Image-2.0 发布：7B 拿下原生 2K，把「图文一体 + 生成编辑统一」推到开源前沿","qwen-image-2-0-7b-native-2k-arena-no1","2026-06-18T08:00:00+00:00",{"id":80,"title":81,"news_slug":82,"published_at":83},"cd88ab8f-afff-4f8f-8edc-ab24715906c6","FLUX.2 [klein] 4B\u002F9B 发布：统一生图编辑，Apache 2.0","flux-2-klein-4b-9b-apache-2-sub-second","2026-06-12T06:30:00+00:00",{"id":85,"title":86,"news_slug":87,"published_at":88},"04d03b80-0a32-4ea1-87df-9248b36653c1","Ideogram 4.0 开源：9.3B 单流 DiT + Qwen3-VL 文本编码器，把排版与文字渲染做到开源第一","ideogram-4-0-9-3b-dit-qwen3-vl-text","2026-06-09T12:00:00+00:00"]