#contents
----
*概要 [#k422715e]
- 生成AIに関して
* Image Generation [#i347afd3]
** Midjorney [#uae6610a]
-- [[/midlibrary>https://midlibrary.io/]] - Midjorney 用のPrompt スタイル実例一覧
** StableDiffusion [#k2e07fbc]
-- [[ASCII.jp : Stable Diffusion入門 from Thailand>https://ascii.jp/serialarticles/3001054/]]
** StableCascade [#pb63bc47]
-- [[StableCascade>https://github.com/Stability-AI/StableCascade]]
-- [[Stable Cascade のご紹介>https://ja.stability.ai/blog/stable-cascade]]
** StreamDiffusion [#z1542fa7]
-- [[GeForce RTX 4090なら100fps超え?噂の爆速画像生成AI環境「StreamDiffusion」を試す>https://pc.watch.impress.co.jp/docs/column/nishikawa/1559782.html]]
** その他 [#u224e999]
-- [[Open-source PixArt-δ image generator spits out high-resolution AI images in 0.5 seconds>https://the-decoder.com/open-source-pixart-%CE%B4-image-generator-spits-out-high-resolution-ai-images-in-0-5-seconds/]] - OSSの高速画像生成器PixArt-δ
-- [[SPAD : Spatially Aware Multiview Diffusers>https://yashkant.github.io/spad/]]
-- [[Announcing Flux by Black Forest Labs: The Next Leap in Text-to-Image Models>https://blog.fal.ai/flux-the-largest-open-sourced-text2img-model-now-available-on-fal/]]
* 2D3D Transform [#l66f6d3f]
-- [[Introducing Stable Fast 3D: Rapid 3D Asset Generation From Single Images>https://stability.ai/news/introducing-stable-fast-3d]]
* Text Generation [#p41085f7]
- [[ArtificialAnalysis.ai>https://artificialanalysis.ai/]] - 各種サービスの性能/速度/価格などの比較
- [[Machine Learning Engineering Open Book>https://github.com/stas00/ml-engineering]] - LLMの学習に関する技術文章
- [[The Rise and Potential of Large Language Model Based Agents: A Survey>https://github.com/WooooDyy/LLM-Agent-Paper-List]] - LLMに関する論文survey
- [[Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text>https://arxiv.org/abs/2401.12070]] - AI生成テキストの検出器
- [[You can now train a 70b language model at home>https://www.answer.ai/posts/2024-03-06-fsdp-qlora.html]] - 70BクラスのLLMを自宅でfinetuningする方法
- [[LLM price compass>https://github.com/arc53/llm-price-compass]] - LLMサービスの価格比較
** Model [#o591d191]
- [[Eagle 7B>https://blog.rwkv.com/p/eagle-7b-soaring-past-transformers]] - 多言語をカバーした2024/01/29時点でのSoA LLMモデル
* Text to Speech [#ad7ed130]
- [[WhisperSpeech>https://github.com/collabora/WhisperSpeech]]
*参考リンク [#p1b1700a]
-[[新清司の「メタバース・プレゼンス」>https://ascii.jp/serialarticles/3000931/]]
-[[Stable Diffusion入門 from Thailand>https://ascii.jp/serialarticles/3001054/]]
-[[西川和久の不定期コラム>https://pc.watch.impress.co.jp/docs/column/nishikawa/]]
-[[AIのソフト一覧 - 窓の杜>https://forest.watch.impress.co.jp/library/nav/genre/ai/]]