画像生成AI(1)からの続き
YouTuberのMattVideoProによれば,現時点でも20以上の画像生成AIサービスが立ち上がっている(下記リスト参照)。たぶん今年の最も重要なトレンドの一つだ。前回は,CrAIyonを試してみた。日本では,Midjouneyが流行っている。1. Google Imagen/Parti (Unreleased) https://parti.research.google/
2. Open AI Dall-E 2 (Closed Beta) https://openai.com/dall-e-2/
3. Stable Diffusion (Free to use) https://huggingface.co/spaces/stabilityai/stable-diffusion4. Simulacrabot (Closed Alpha) https://stability.ai/simulacrabot/terms-of-use
5. Midjourney (Free Trial, paid access) https://www.midjourney.com/app/
6. Shonenkov AI (Free to Use) https://t.me/shonenkovAI (JOIN MY DISCORD FOR LINK)
7. Meta Make-A-Scene (very Closed Beta) https://about.fb.com/news/2022/07/metas-new-ai-research-8. tool-turns-ideas-into-art/
9. Microsoft VQ Diffusion (Free to use) https://replicate.com/cjwbw/vq-diffusion
10. Deep AI Text to Image (Free Access) https://deepai.org/machine-learning-model/text2img
11. MindsEye beta (by multimodal.art) (Free to use) https://colab.research.google.com/drive/1cg0LZ5OfN9LAIB37Xq49as0fSJxcKtC5
12. CrAIyon (Free to use) https://www.craiyon.com/
13. Min-dalle (Free & Paid) https://replicate.com/kuprel/min-dalle
14. Dall E Flow (Free to use) https://github.com/jina-ai/dalle-flow
15. Wombo (Free & Paid) https://app.wombo.art/
16. Laion AI Erlich (Free & Paid) https://replicate.com/laion-ai/erlich
17. Latent Diffusion (Free to use) https://huggingface.co/spaces/multimodalart/latentdiffusion
18. Glid-3-xl (Free & Paid) https://replicate.com/jack000/glid-3-xl
19. Night Cafe (Free & Paid) https://creator.nightcafe.studio/explore
20. Disco Diffusion (Free & Paid) https://colab.research.google.com/github/alembics/disco-diffusion/blob/main/Disco_Diffusion.ipynb
21. Cog View 2 (Free & Paid) https://replicate.com/thudm/cogview2
22. Pixray (Free & Paid) https://replicate.com/pixray/text2image
23.Hot Pot AI (free & Paid) https://hotpot.ai/art-maker
24. Nvidia gaugan2 (Free to Use) http://gaugan.org/gaugan2/