imported>Hrs81458 来自 2026年6月1日 (一) 08:07

2026-06-01T08:07:04Z

新页面

{{Infobox software
| name = Flux
| logo =
| logo caption =
| screenshot = The Path to the Black Forest (FLUX 1.1 Pro Ultra).webp
| caption = 由 Flux 1.1 Pro（Ultra 模式）生成的圖像。提示詞：<code>請生成一張你覺得能代表你自己的圖像。</code>
| author = 黑森林實驗室（{{langx|en|Black Forest Labs}}）
| developer = 黑森林實驗室
| released = 2024年8月
| programming language =
| operating system =
| genre = [[文字轉圖像模型]]
| license = Apache License（Schnell版本）、非商業授權（Dev版本）、專有授權（Pro版本）
| repo =
| website = {{URL|https://blackforestlabs.ai/}}
| screenshot alt = AI 生成的數位圖像，主題為通往森林的小徑，背景為山脈
| latest release version = Flux 1.1 Pro（模型）<ref name="release-version">{{cite web|title=Announcing FLUX1.1 [pro] and the BFL API|url=https://blackforestlabs.ai/announcing-flux-1-1-pro-and-the-bfl-api/|website=Black Forest Labs|date=2024-10-02 |access-date=2024-11-17|archive-date=|archive-url=}}</ref>
| latest release date = 2024 年 10 月 2 日
}}

'''Flux'''（亦稱FLUX.1）是由總部位於[[德國]][[弗赖堡行政区|弗賴堡]]的黑森林實驗室（{{langx|en|Black Forest Labs}}）所開發的[[文本轉圖像生成模型|文字轉圖像模型]]。該公司由多位前[[Stability AI]]員工創辦。與其他同類型模型相同，Flux能夠根據[[自然語言]]輸入（即[[提示工程|提示詞]]）生成圖像。

== 歷史 ==
黑森林實驗室於2024年成立，創辦人為[[Stability AI]]前員工羅賓·隆巴赫（Robin Rombach）、安德烈亞斯·布拉特曼（Andreas Blattmann）和帕特里克·埃塞爾（Patrick Esser）。<ref name="DieZeit">{{Cite news |last=Killian |first=Nicolas |date=2024-08-27 |title=Black Forest Labs: Sie sind ein Teil von jener Kraft |url=https://www.zeit.de/digital/datenschutz/2024-08/black-forest-labs-ki-bildgenerator-elon-musk |url-access=subscription |url-status=live |archive-url=https://web.archive.org/web/20241004170543/https://www.zeit.de/digital/datenschutz/2024-08/black-forest-labs-ki-bildgenerator-elon-musk |archive-date=2024-10-04 |access-date=2024-11-17 |work=[[Die Zeit]] |language=de |issn=0044-2070}}</ref><ref name="PetaPixel">{{Cite web |title=AI Image Generator Made by Stable Diffusion Inventors on Par With Midjourney and DALL-E |url=https://petapixel.com/2024/08/05/ai-image-generator-made-by-stable-diffusion-inventors-on-par-with-midjourney-and-dall-e-flux1-black-forest-labs/ |website=[[PetaPixel]] |date=2024-08-05 |language=en |last=Growcoot |first=Matt |access-date=2024-11-17}}</ref>他們早年在德國[[慕尼黑大學]]擔任[[比約恩·奧默]]的研究助理，專門研究人工智慧圖像生成技術。<ref name="AlleAktien">{{Cite web |title=Black Forest Labs unter Beschuss: Schockierende KI-Bilder sorgen für… |url=https://www.alleaktien.com/news/black-forest-labs-unter-beschuss-schockierende-ki-bilder-sorgen-fur-emporung |website=AlleAktien |date=2024-08-22 |language=de |access-date=2024-11-17}}</ref><ref name="TrendAT">{{Cite web |title=Black Forest Labs: KI-Tools aus dem Schwarzwald |url=https://www.trend.at/tools/black-forest-labs |website=trend.at |date=2024-08-08 |language=de |last=Hermes |first=Ann Kathrin |access-date=2024-11-17}}</ref><ref name="CapitalDE">{{Cite web |title=Black Forest Labs: Die Schwarzwald-KI, auf die Elon Musk setzt |url=https://www.capital.de/wirtschaft-politik/black-forest-labs--ki-aus-dem-schwarzwald-schlaegt-openai-34979066.html |website=[[Capital (German magazine)|Capital.de]] |date=2024-08-15 |language=de |last=Schwär |first=Hannah |access-date=2024-11-17}}</ref>2022 年，他們發表了相關研究成果，並促成了[[Stable Diffusion]]的誕生。<ref name="CapitalDE" /><ref name="Ommer">{{Cite web |title=High-Resolution Image Synthesis with Latent Diffusion Models |url=https://ommer-lab.com/research/latent-diffusion-models/ |website=Computer Vision & Learning Group |language=en-US |url-status=live |archive-url=https://web.archive.org/web/20241116192358/https://ommer-lab.com/research/latent-diffusion-models/ |archive-date=2024-11-16 |access-date=2024-11-17}}</ref>

黑森林實驗室的投資者包括創投公司[[安德里森·霍羅維茲]]，以及{{le|布倫丹·艾瑞比|Brendan Iribe}}、{{le|邁克爾·奧維茨|Michael Ovitz}}、{{le|陳嘉興|Garry Tan}}和{{le|弗拉德連·寇頓|Vladlen Koltun}}。<ref name="Announcement">{{Cite web |title=Announcing Black Forest Labs |url=https://blackforestlabs.ai/announcing-black-forest-labs/ |website=Black Forest Labs |date=2024-08-01 |language=en-US |url-status=live |archive-url=https://web.archive.org/web/20241117160834/https://blackforestlabs.ai/announcing-black-forest-labs/ |archive-date=2024-11-17 |access-date=2024-11-17}}</ref>在創立初期，公司获得3100萬美元的投資。<ref name="TrendingTopics">{{Cite web |title=Black Forest Labs: 31 Mio. Dollar für Herausforderer von OpenAI und Midjourney |url=https://www.trendingtopics.eu/black-forest-labs-31-mio-dollar-fuer-herausforderer-von-openai-und-midjourney/ |website=Trending Topics |date=2024-08-12 |language=de |last=Steinschaden |first=Jakob |url-status=live |archive-url=https://web.archive.org/web/20240828133326/https://www.trendingtopics.eu/black-forest-labs-31-mio-dollar-fuer-herausforderer-von-openai-und-midjourney/ |archive-date=2024-08-28 |access-date=2024-11-17}}</ref><ref name="VentureBeat-funding">{{Cite web |title=Stable Diffusion creators launch Black Forest Labs, secure $31M for FLUX.1 AI image generator |url=https://venturebeat.com/ai/stable-diffusion-creators-launch-black-forest-labs-secure-31m-for-flux-1-ai-image-generator/ |website=[[VentureBeat]] |date=2024-08-01 |language=en-US |last=Nuñez |first=Michael |url-status=live |archive-url=https://web.archive.org/web/20241008120037/https://venturebeat.com/ai/stable-diffusion-creators-launch-black-forest-labs-secure-31m-for-flux-1-ai-image-generator/ |archive-date=2024-10-08 |access-date=2024-11-17}}</ref>

2024年8月，Flux被整合進由[[xAI]]開發的[[聊天機器人]][[Grok]]，並作為 X（前推特）付費功能的一部分提供。<ref name="Meedia">{{Cite web |title=Generative AI. Black Forest Labs und Flux.1: Vom Superstar zum Buhmann in fünf Tagen |url=https://meedia.de/news/beitrag/17472-black-forest-labs-und-flux-1-vom-superstar-zum-buhmann-in-fuenf-tagen.html |website=MEEDIA |language=de |last=Puscher |first=Frank |url-access=subscription |url-status=live |archive-url=https://web.archive.org/web/20240927210951/https://meedia.de/news/beitrag/17472-black-forest-labs-und-flux-1-vom-superstar-zum-buhmann-in-fuenf-tagen.html |archive-date=2024-09-27 |access-date=2024-11-17}}</ref><ref name="Handelsblatt">{{Cite web |title=Flux.1 – ein deutscher KI-Bildgenerator dreht mit Grok frei |url=https://www.handelsblatt.com/technik/ki/xai-kooperation-flux1-deutscher-ki-bildgenerator-dreht-mit-grok-frei/100059178.html |website=[[Handelsblatt]] |language=de |last=Bomke |first=Luisa |url-status=live |archive-url=https://web.archive.org/web/20240830103514/https://www.handelsblatt.com/technik/ki/xai-kooperation-flux1-deutscher-ki-bildgenerator-dreht-mit-grok-frei/100059178.html |archive-date=2024-08-30 |access-date=2024-11-17}}</ref><ref name="TheVerge">{{Cite web |title=xAI's new Grok-2 chatbots bring AI image generation to X |url=https://www.theverge.com/2024/8/14/24220127/grok-ai-chatbot-beta-image-generation-x-xai-update |website=[[The Verge]] |date=2024-08-14 |language=en |last=Weatherbed |first=Jess |url-status=live |archive-url=https://web.archive.org/web/20241117000048/https://www.theverge.com/2024/8/14/24220127/grok-ai-chatbot-beta-image-generation-x-xai-update |archive-date=2024-11-17 |access-date=2024-11-17}}</ref><ref name="Bloomberg">{{Cite news |last=Metz |first=Rachel |date=2024-08-21 |title=This Tiny Startup Is Helping Musk's Grok With Image Generation |url=https://www.bloomberg.com/news/articles/2024-08-21/this-tiny-startup-is-helping-musk-s-grok-with-image-generation |url-access=subscription |access-date=2024-11-19 |work=[[Bloomberg News]] |language=en}}</ref>Grok於同年12月改用自家開發的文字轉圖像模型{{tsl|en|Aurora (text-to-image model)|Aurora}}。<ref name="Grok-Aurora">{{Cite web |title=X gives Grok a new photorealistic AI image generator |url=https://www.theverge.com/2024/12/7/24315644/grok-x-aurora-ai-image-generator-xai |website=The Verge |date=2024-12-07 |language=en |last=Davis |first=Wes |url-status=live |archive-url=https://web.archive.org/web/20241212193314/https://www.theverge.com/2024/12/7/24315644/grok-x-aurora-ai-image-generator-xai |archive-date=2024-12-12 |access-date=2024-12-10}}</ref>

2024年11月18日，[[Mistral AI]]宣布，其聊天機器人Le Chat已整合Flux Pro作為圖像生成模型。<ref name="Mistral-LeChat">{{Cite web |title=Mistral has entered the chat |url=https://mistral.ai/news/mistral-chat/ |website=[[Mistral AI]] |date=2024-11-18 |language=en-us |access-date=2024-12-11}}</ref><ref name="VentureBeat-LeChat">{{Cite web |title=Mistral unleashes Pixtral Large and upgrades Le Chat into full-on ChatGPT competitor |url=https://venturebeat.com/ai/mistral-unleashes-pixtral-large-and-upgrades-le-chat-into-full-on-chatgpt-competitor/ |website=VentureBeat |date=2024-11-18 |language=en-US |last=Franzen |first=Carl |access-date=2024-12-11}}</ref>

2024年11月21日，黑森林實驗室宣布推出圖像編輯工具Flux.1 Tools，可搭配現有Flux模型使用，這套工具包括：

* Flux.1 Fill（用於補圖與延伸圖像邊緣，即[[图像修复]]/outpainting）；
* Flux.1 Depth（依據輸入圖像的{{tsl|en|depth map|深度圖}}與提示詞進行控制生成）；
* Flux.1 Canny（依據輸入圖像的邊緣線條進行控制生成）；
* Flux.1 Redux（將不同輸入圖像與提示詞混合生成新圖像）。

這些工具皆提供Dev（開發者）版與Pro（專業）版兩種選擇。<ref name="Tools">{{Cite web |title=Introducing FLUX.1 Tools |url=https://blackforestlabs.ai/flux-1-tools/ |website=Black Forest Labs |date=2024-11-21 |language=en-US |url-status=live |archive-url=https://web.archive.org/web/20241126040130/https://blackforestlabs.ai/flux-1-tools/ |archive-date=2024-11-26 |access-date=2024-12-13}}</ref><ref name="TheDecoder-Tools">{{Cite web |title=Black Forest Labs expands FLUX.1 with four new AI tools for image editing |url=https://the-decoder.com/black-forest-labs-expands-flux-1-with-four-new-ai-tools-for-image-editing/ |website=The Decoder |date=2024-11-22 |language=en-US |last=Bastian |first=Matthias |url-status=live |archive-url=https://web.archive.org/web/20241122224517/https://the-decoder.com/black-forest-labs-expands-flux-1-with-four-new-ai-tools-for-image-editing/ |archive-date=2024-11-22 |access-date=2024-12-15}}</ref>

2025 年 1 月，黑森林實驗室宣布與[[輝達]]合作，將Flux模型納入其[[Blackwell (微架构)|Blackwall]]微架構的基礎模型。<ref name="VentureBeat-Nvidia">{{Cite web |title=Nvidia unveils AI foundation models running on RTX AI PCs |url=https://venturebeat.com/ai/nvidia-unveils-ai-foundation-models-running-on-rtx-ai-pcs/ |website=VentureBeat |date=2025-01-07 |language=en-US |last=Takahashi |first=Dean |url-status=live |archive-url=https://web.archive.org/web/20250109215759/https://venturebeat.com/ai/nvidia-unveils-ai-foundation-models-running-on-rtx-ai-pcs/ |archive-date=2025-01-09 |access-date=2025-01-19}}</ref>同時，該公司推出Flux Pro微調API，供使用者自訂與{{tsl|en|Fine-tuning (deep learning)|微調圖像}}生成內容，並與德國媒體公司 {{tsl|en|Hubert Burda Media}}合作，將 Flux Pro 應用於內容製作。<ref name="VentureBeat-ProFinetuning">{{Cite web |title=You can now fine-tune your own version of AI image maker Flux with just 5 images |url=https://venturebeat.com/ai/you-can-now-fine-tune-your-own-version-of-ai-image-maker-flux-with-just-5-images/ |website=VentureBeat |date=2025-01-16 |language=en-US |last=Franzen |first=Carl |url-status=live |archive-url=https://web.archive.org/web/20250124083654/https://venturebeat.com/ai/you-can-now-fine-tune-your-own-version-of-ai-image-maker-flux-with-just-5-images/ |archive-date=2025-01-24 |access-date=2025-01-19}}</ref>

== 模型 ==
Flux是一系列基於修正型流式轉換器（{{langx|en|rectified flow transformer}}）架構開發的文字轉圖像模型，參數規模達120億。<ref name="Announcement" /><ref name="Hugging Face">{{Cite web |title=black-forest-labs/FLUX.1-dev · Hugging Face |url=https://huggingface.co/black-forest-labs/FLUX.1-dev |website=Hugging Face |date=2025-04-19 |language=en-US |access-date=2025-04-19}}</ref>

根據不同版本，Flux提供三種授權模式：

* Schnell版：[[開源授權|開源]]，採用{{tsl|en|Apache License|Apache授權}}；
* Dev版：提供[[原始碼]]，僅限非商業用途；
* Pro版：專有授權，僅透過[[API]]提供給第三方用戶<ref name="Get-Flux">{{Cite web |title=Get Flux |url=https://blackforestlabs.ai/#get-flux |website=Black Forest Labs |language=en-US |url-status=live |archive-url=https://web.archive.org/web/20241116053205/https://blackforestlabs.ai/#get-flux |archive-date=2024-11-16 |access-date=2024-11-17}}</ref><ref name="TechCrunch-API">{{Cite web |title=Black Forest Labs, the startup behind Grok's image generator, releases an API |url=https://techcrunch.com/2024/10/03/black-forest-labs-the-startup-behind-groks-image-generator-releases-an-api/ |website=[[TechCrunch]] |date=2024-10-03 |language=en-US |last=Wiggers |first=Kyle |url-status=live |archive-url=https://web.archive.org/web/20241004040824/https://techcrunch.com/2024/10/03/black-forest-labs-the-startup-behind-groks-image-generator-releases-an-api/ |archive-date=2024-10-04 |access-date=2024-11-17}}</ref>無論使用哪個版本，生成出的圖像著作權均屬於使用者。<ref name="Dev-licence">{{Cite web |title=flux/model_licenses/LICENSE-FLUX1-dev at main · black-forest-labs/flux |url=https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev |website=GitHub |language=en |url-status=live |archive-url=https://web.archive.org/web/20240915222202/https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev |archive-date=2024-09-15 |access-date=2024-11-18 |quote="Outputs. We claim no ownership rights in and to the Outputs. You are solely responsible for the Outputs you generate and their subsequent uses in accordance with this License. You may use Output for any purpose (including for commercial purposes), except as expressly prohibited herein. You may not use the Output to train, fine-tune or distill a model that is competitive with the FLUX.1 [dev] Model."}}</ref><ref name="Pro-API-Agreement">{{Cite web |title=API Agreement - BFL Docs (Pro) |url=https://docs.bfl.ml/agreement/ |website=Black Forest Labs |date=2024-08-01 |url-status=live |archive-url=https://web.archive.org/web/20241003191037/https://docs.bfl.ml/agreement/ |archive-date=2024-10-03 |access-date=2024-11-18 |quote=Output. Company claims no ownership rights in and to the Outputs, and Developer and Users may use the Output for their own personal or commercial purposes, subject to any restrictions set forth herein or in the Flux Service Terms. For the avoidance of doubt, Outputs do not include any components of the Flux API or the Flux AI model, such as its weights or parameters.}}</ref>

使用者可以在線上或本機透過介面如{{tsl|en|ComfyUI}}或{{tsl|en|Stable Diffusion WebUI Forge}}（Automatic1111 WebUI 的{{tsl|en|Fork (software development)|改良版}}）來使用這些模型。<ref name="Announcement" /><ref name="ASCII-Forge">{{cite web |title=話題の画像生成AI「FLUX.1」をStable Diffusion用の「WebUI Forge」で動かす（高速化も試してみました） (1/6) |url=https://ascii.jp/elem/000/004/215/4215695/ |website=ASCII.jp |date=2024-08-18 |language=ja |author1=田口和裕 |access-date=2024-11-21 |publisher=[[ASCII Media Works]]}}</ref>

改良後的旗艦模型Flux 1.1 Pro於2024年10月2日推出。<ref name="release-1.1-pro">{{cite web |title=Announcing FLUX1.1 [pro] and the BFL API |url=https://blackforestlabs.ai/announcing-flux-1-1-pro-and-the-bfl-api/ |website=Black Forest Labs |date=2024-10-02 |archive-url= |archive-date= |access-date=2024-11-17}}</ref><ref name="VentureBeat-1.1-pro">{{Cite web |title=Black Forest Labs releases Flux 1.1 Pro and an API |url=https://venturebeat.com/ai/black-forest-labs-releases-flux-1-1-pro-and-an-api/ |website=VentureBeat |date=2024-10-03 |language=en-US |last=Franzen |first=Carl |access-date=2024-11-17}}</ref>2024年11月6日，新增兩種進階模式：

* Ultra模式：可在不降低生成速度的情況下，產生解析度提高四倍、最高達 400 萬像素的圖像；
* Raw模式：能生成類似{{tsl|en|candid photography|自然抓拍風格}}的高度擬真圖像<ref name="PetaPixel-1.1-pro">{{Cite web |title=Flux AI Introduces Raw Mode That 'Captures the Genuine Feel of Candid Photography' |url=https://petapixel.com/2024/11/07/flux-ai-introduces-raw-mode-that-captures-the-genuine-feel-of-candid-photography/ |website=PetaPixel |date=2024-11-07 |language=en |last=Growcoot |first=Matt |access-date=2024-11-19}}</ref><ref name="TheDecoder-raw">{{Cite web |title=Flux 1.1 Pro AI image model adds "amateur" RAW photo mode and 4K image generation |url=https://the-decoder.com/flux-1-1-pro-ai-image-model-adds-amateur-raw-photo-mode-and-4k-image-generation/ |website=The Decoder |date=2024-11-06 |language=en-US |last=Bastian |first=Matthias |access-date=2024-11-17}}</ref><ref name="1.1-ultra-raw">{{Cite web |title=Introducing FLUX1.1 [pro] Ultra and Raw Modes |url=https://blackforestlabs.ai/flux-1-1-ultra/ |website=Black Forest Labs |date=2024-11-06 |language=en-US |url-status=live |archive-url=https://web.archive.org/web/20241112145336/https://blackforestlabs.ai/flux-1-1-ultra/ |archive-date=2024-11-12 |access-date=2024-11-17}}</ref>

此外，Flux團隊正在開發的[[文本到视频生成模型|文字轉影片模型]]SOTA，原預計於2024年底推出。<ref name="Announcement" />

== 評價 ==
根據《[[Ars Technica]]》的測試，Flux.1 Dev與Pro模型在提示詞還原度方面可與[[DALL-E|DALL-E 3]]匹敵，而圖像寫實程度則接近[[Midjourney]] 6。相較於 Stable Diffusion XL，Flux對人手的細節呈現更為穩定。<ref name="ArsTechnica">{{Cite web |title=FLUX: This new AI image generator is eerily good at creating human hands |url=https://arstechnica.com/information-technology/2024/08/flux-this-new-ai-image-generator-is-eerily-good-at-creating-human-hands/ |website=[[Ars Technica]] |date=2024-08-02 |language=en-US |last=Edwards |first=Benj |access-date=2024-11-17}}</ref>

== 爭議 ==
有批評指出Flux生成圖像過於寫實。媒體報導指出，其生成內容涵蓋從[[川普]]持槍的圖像，到令人不安的場景，引發外界對其倫理與濫用風險的爭議。<ref name="AlleAktien" /><ref name="TheVerge" />

模型推出後，X （前[[推特]]）出現大量由Flux所生成的圖像，黑森林實驗室並未透露其訓練資料的具體來源。<ref name="PetaPixel-1.1-pro" /><ref name="TechCrunch-BFL">{{Cite web |title=Meet Black Forest Labs, the startup powering Elon Musk's unhinged AI image generator |url=https://techcrunch.com/2024/08/14/meet-black-forest-labs-the-startup-powering-elon-musks-unhinged-ai-image-generator/ |website=TechCrunch |date=2024-08-14 |language=en-US |last=Zeff |first=Maxwell |url-status=live |archive-url=https://web.archive.org/web/20241117003305/https://techcrunch.com/2024/08/14/meet-black-forest-labs-the-startup-powering-elon-musks-unhinged-ai-image-generator/ |archive-date=2024-11-17 |access-date=2024-11-17}}</ref><ref name="RND">{{Cite web |title=Drogen, Bomben und Gewalt: KI-Bildgenerator von Elon Musk zeigt alles – mit deutscher Technik |url=https://www.rnd.de/digital/drogen-bomben-und-gewalt-ki-bildgenerator-von-elon-musk-zeigt-alles-mit-deutscher-technik-O4U7367ONNA4LF43GNMVNJARBI.html |website=RND.de |date=2024-08-16 |language=de |last=Schwarzer |first=Matthias |access-date=2024-11-17}}</ref>《Ars Technica》懷疑Flux是在未經授權的情況下，從網路上大量{{tsl|en|Web scraping|蒐集圖像}}所訓練而成，此作法在法律層面存在爭議。<ref name="ArsTechnica" /><ref name="Docma">{{Cite web |title=FLUX.1: Neuer KI-Bildgenerator |url=https://www.docma.info/ki/flux1-neuer-ki-bildgenerator |website=DOCMA |date=2024-08-07 |language=de |last=Künne |first=Christoph |url-status=live |archive-url=https://web.archive.org/web/20240831113513/https://www.docma.info/ki/flux1-neuer-ki-bildgenerator |archive-date=2024-08-31 |access-date=2024-11-17}}</ref>

== 第三方整合 ==
雖然黑森林實驗室未在其官方網站提供直接存取模型的方式，但Flux模型已在多個第三方平台上廣泛提供，供創作者與專業人士使用，包括[[Hugging Face]]<ref>{{cite web |title=Black Forest Labs on Hugging Face |url=https://huggingface.co/black-forest-labs |website=Hugging Face |url-status=live |archive-url=https://web.archive.org/web/20250202084151/https://huggingface.co/black-forest-labs |archive-date=2025-02-02 |access-date=2025-01-05}}</ref>和Replicate<ref>{{cite web |title=Flux Collection on Replicate |url=https://replicate.com/collections/flux |website=Replicate |url-status=live |archive-url=https://web.archive.org/web/20250125142958/https://replicate.com/collections/flux |archive-date=2025-01-25 |access-date=2025-01-05}}</ref>等平台。

== 參考資料 ==
{{reflist|30em}}

== 外部連結 ==
{{Commons category}}

* {{Official website|https://blackforestlabs.ai/}}
* [https://huggingface.co/black-forest-labs Hugging Face的flux模型]
* [https://replicate.com/collections/flux Flux models on Replicate]
* [https://fal.ai/models?keywords=flux FAL.ai的flux模型]

[[Category:人工智慧藝術]]
[[Category:使用Apache許可證的軟體]]
[[Category:开源人工智能]]

Flux - 版本历史

imported>Hrs81458 来自 2026年6月1日 (一) 08:07