
After seeing the new detailed prompting methods flux uses to generate images, I decided to see if it was possible to train other models to accept JoyCaption style prompts. I will attempt to train multiple common non-Flux checkpoints like Pony, SDXL, and SD15 to accept more advanced prompts. Check each version's version details to see what it does and how it should be used.
描述:
Pony version trained at 256X256 using kohayaSS, seems to improve JoyCaption style prompt gens by a bit, but doesnt help with text any, which is sad. Seems to work best around 1.0 strength, but I have also gotten good results around 0.4-0.6. Definitely needs more work.
训练词语:
名称: JoyCaptionPonyBeta.safetensors
大小 (KB): 56074
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success