A Flux fine-tune of https://replicate.com/zeke the real-life human. Use "ZIKI" in the prompt to activate the trained style.

Guesses your age based on a photo

A tiny model for testing out Cog

Detect whether a GitHub user has a custom or default avatar

A fork of pixray/pixray for trying out Cog's new Predictor API

Generate haiku. A tiny model for testing out Replicate.

A test model that generates Haiku (and yields output one word a time)

A model for testing pydantic cog that generates images.

A model for testing pydantic cog that yields images one word at a time.

My own personal https://replicate.com/replicate/dreambooth

A DreamBooth model trained using GitHub Actions. Prompt identifier is `dgg`

My own personal fork of Stable Diffusion

A fine-tuned version SDXL for generating loteria cards

Create your own variants of "this is fine" 🔥☕️🐕

SDXL finetune (IIRC?) based on the Adventure Time show

SDXL fine-tuned on characters and objects from Richard Scarry's Busytown

My own personal copy of daanelson/whisperx

Stable Diffusion 3 with Differential Diffusion inpainting (experimental)

This model is not great. Check out this other one that's better: https://replicate.com/apolinario/flux-tarot-v1

Use trigger word ziki-2024-08-30 to activate the trained LoRA style.