Lola is an original, fully synthetic character LoRA for Z-Image, trained on the BigLove Z checkpoint.

🛠️ Made with LoRA Dataset Studio — the open-source tool I use to build and train all my character LoRAs (dataset curation, auto-captioning, face-similarity scoring, training, checkpoint testing, all in one UI). Read the write-up / tutorial.

💬 Join my Discord: discord.gg/wrAWFTPJe

This LoRA is face-centered: it locks Lola's facial identity with strong consistency from shot to shot, while leaving body, silhouette, hair style and outfit completely free to your prompt. Change the hair color, the setting, the framing - the face stays Lola.

Trigger word: lola3869 (put it at the start of your prompt).

Training: 3400 steps / 121 epochs on BigLove ZT3 (Z-Image Turbo family). All example images were generated with this exact LoRA at strength 1.0 on Z-Image Turbo checkpoints.

Recommended settings: strength 1.0 when used alone.

Pro tip - blend characters to design new faces: it is really interesting to combine several of my character LoRAs together at low strength, around 0.4 to 0.45 each. The identities merge into brand new, gorgeous faces that keep the photorealistic consistency of each LoRA. A great way to create your own original character from existing ones.