elizabeth_olsen
Total score: 2.3 (3 stars) available
Details: 3 available
The 2D model is more similar to her
Style: 2 partially available
Some are too 3D and difficult to generate a 2D style.
Failure rate: 2 partially available
The training data seems somewhat monolithic. Under different models, the clothing and background are highly similar
The test uses only a single trigger word, generating images with 2 fixed seeds. Examine the initial performance of the character LoRa itself. There are three objective dimensions: detail, style, and failure. 1 Not available 2 Partially available 3 Available 4 Excellent 5 Perfect . The overall score matches Civitai's five-star rating.
总分:2.3(3星 )可用
细节:3 可用
2D模型中和她的相似度更高
风格:2 部分可用
有些过于3D化,较难生成2D风格。
失败率:2 部分可用
训练数据似乎有些单一。在不同模型下,服装和背景相似度很高
该测试仅使用单个trigger word,用2个固定种子生成图像。考察人物LoRa 自身的初始性能.有三个客观维度:细节、风格和失败。1 不可用 2 部分可用 3 可用 4 出色 5 完美 。总分和Civitai的五星匹配。