
Test model, I wanted to see if merging two of my favorite models would increase prompt adherence while still keeping its imagination. It is a Pony model, but I've linked the models I merged in the suggested resources, they are great models on their own!
It has a bit of a watermark problem, but they don't seem to be too intrusive and are usually easily fixed with a bit of inpainting.
You should use regular Pony prompts:
score_9, score_8_up, score_7_up, rating_tag, BREAK
and for negatives I recommend a base of:
score_6, score_5, score_4, etc.
But please experiment, I'd love to hear your thoughts!
描述:
训练词语:
名称: indigodreamxl_v10.safetensors
大小 (KB): 6775438
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: sdxl_vae.safetensors
大小 (KB): 326798
类型: VAE
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success