免費註冊,立即獲得 10,000 點數

新手創作點數,註冊當天到帳

SDXL

Proteus

Proteus - AI Model封面圖片

免費註冊,立即獲得 10,000 點數

新手創作點數,註冊當天到帳

上傳時間
2024年3月4日 下午5:10
使用數
337
評論
非常好  (1)
許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

推薦 LoRA

描述

also on huggingface: https://huggingface.co/dataautogpt3/ProteusV0.4This update enhances stylistic capabilities, similar to Midjourney's approach, rather than advancing prompt comprehension. Methods used do not infringe on any copyrighted material.some issues have been noted "being too stylistic/creative. i am working solving those as of now and putting V0.4 into beta as to make sure people know that issues are abound regarding the model for now.finetuned/trained on a total of 400k+ images at this point._______________________________________________________________________Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its core functionalities to deliver superior outcomes. Key areas of advancement include heightened responsiveness to prompts and augmented creative capacities. To achieve this, it was fine-tuned using approximately 220,000 GPTV captioned images from copyright-free stock images (with some anime included), which were then normalized. Additionally, DPO (Direct Preference Optimization) was employed through a collection of 10,000 carefully selected high-quality, AI-generated image pairs.In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.Settings for ProteusUse these settings for the best results with ProteusV0.4:CFG Scale: Use a CFG scale of 4 to 6Steps: 20 to 60 steps for more detail, 20 steps for faster results.Sampler: DPM++ 2M SDEScheduler: KarrasResolution: 1280x1280 or 1024x1024please also consider using these keep words to improve your prompts: best quality, HD, ~~aesthetic~~

留言

由 Proteus 製作的作品

1