merges.txt and vocab.json | 90k Random Tokens

Rocket_AIRocket_AI
3
156
merges
model-image-0
model-image-1
model-image-2
model-image-3
model-image-4
model-image-5
model-image-6
model-image-7
model-image-8
model-image-9
model-image-10
model-image-11
model-image-12
model-image-13
model-image-14

详情

下载文件 (1)

模型描述

This is merges.txt (recognizable combinations of two tokens) and vocab.json (individual tokens) from the SDXL tokenizer that has been cleaned up to use as a wildcard.

What's the point of this? Bit of fun innit. You can also use this to force z-image into producing more variations. Workflow here: (soon)

此模型生成的图像