Ernie V1 was trained with Ernie base model. Images were generated with the turbo model with the strength of 0.8-0.95. You can use this with any turbo/base model. If not let me know. You can use the trigger word, if you want. It will change the images a bit.
Description
Play with the lora strength, try 0.7-1.0.
Text encoder I use:
Triangle104/Josiefied-Qwen3-4B-abliterated-v2-Q8_0-GGUF