更多AI前沿科技资讯,请关注我们:
鼓励大家在抱脸上下载,但如果不能魔法,可上镜像站下载:https://hf-mirror.com/ali-vilab/In-Context-LoRA
下载后放入。放到以下路径。
[MOVIE-SHOTS] In a vibrant festival, [SCENE-1] we find <Leo>, a shy boy, standing at the edge of a bustling carnival, eyes wide with awe at the colorful rides and laughter, [SCENE-2] transitioning to him reluctantly trying a daring game, his friends cheering him on, [SCENE-3] culminating in a triumphant moment as he wins a giant stuffed bear, his face beaming with pride as he holds it up for all to see.
中文翻译一下:
[电影镜头]在一个充满活力的节日,
[场景-1]我们发现<Leo>,一个害羞的男孩,站在一个繁华的狂欢节的边缘,眼睛睁得大大的,对五颜六色的游乐设施和笑声充满敬畏,
[场景-2]过渡到他不情愿地尝试一个大胆的游戏,他的朋友们为他欢呼,
[场景-3]在一个胜利的时刻达到高潮,因为他赢得了一个巨大的毛绒熊,他的脸上洋溢着骄傲,因为他把它举起来让所有人看到。
工作流生成以下结果:
[场景-1]我们发现<Leo>,一个害羞的男孩,站在一个繁华的狂欢节的边缘,眼睛睁得大大的,对五颜六色的游乐设施和笑声充满敬畏,
[场景-2]过渡到他不情愿地尝试一个大胆的游戏,他的朋友们为他欢呼,
[场景-3]在一个胜利的时刻达到高潮,因为他赢得了一个巨大的毛绒熊,他的脸上洋溢着骄傲,因为他把它举起来让所有人看到。
不错不错,连贯与一致,人物从表现上看是几乎一致的,不能说百分百,衣服背包都有。也很好地遵守提示词的内容来生图。
在生成以上结果时候,我就在想是否能接入pulid来控制人物的脸!于是我加入了pulid来测试。
测试结果可以看出,崩的。我觉得既然是分开10个模型,那它的微调重点是已经区分开的,于是,在换脸的话我还是用它的人像摄影微调的LORA吧。
输入提示词:
This [FOUR-PANEL] image illustrates a young artist's creative process in a bright and inspiring studio; [TOP-LEFT] she stands before a large canvas, brush in hand, adding vibrant colors to a partially completed painting, [TOP-RIGHT] she sits at a cluttered wooden table, sketching ideas in a notebook with various art supplies scattered around, [BOTTOM-LEFT] she takes a moment to step back and observe her work, adjusting her glasses thoughtfully, and [BOTTOM-RIGHT] she experiments with different textures by mixing paints directly on the palette, her focused expression showcasing her dedication to her craft.
输出结果如下:
可以看到,我打码了两张,因为崩了。不堪入目。
再测试下,
加入pulid后影响了生图质量。加入了其它LORA后它还是具有不稳定性
我们直接测试不加入的换脸的结果,因为我们测试了两次都影响了原来的质量,但有些画面是可以生成的,所以我们换个思路就是生图之后进行换脸即可。
看,这样效果好多了。非常棒!
以下我还测试了视觉识别LORA,因为lora太多,日后根据需要使用,大家可以下载来进行体验!
下图是视觉识别测试结果:
The pair of images showcases the joyful identity of a produce brand, [IMAGE1] showing a smiling pineapple graphic and the brand name “CloserAI” in a fun, casual font on a light aqua background; while [IMAGE2] translates the design onto a reusable shopping tote with the pineapple logo in black, held by a person in a market setting, emphasizing the brand’s approachable and eco-friendly vibe.
效果非常棒。建议大家体验使用。并构思项目落地。
以上是closerAI团队基于stable diffusion comfyUI 制作作的closerAI iClora 上下文文生图工作流介绍以及阿里推出的In-Context LoRA微调文生图模型的介绍,大家可以根据工作流思路进行尝试搭建和体验In-Context LoRA。
当然,也可以在我们closerAI会员站上获取对应的工作流。
更多AI前沿科技资讯,请关注我们:
点击“阅读原文”跳转工作流