This is the optimized All-in-One (AIO) version of Z Image Base with only 8 steps. The Diffusion model, Text Encoder, and VAE are fully integrated within a single architecture for maximum efficiency and ease of use.
Constructive feedback and technical reports regarding the model's performance are highly appreciated and can be submitted in the comments section.
ComfyUI Reccomended
Base Model: https://huggingface.co/Tongyi-MAI/Z-Image
Settings : CFG : 1 | | Steps : 8 | | Sampler : Euler/Euler Ancestral | |
Support & Custom Requests:
Processing, testing, and optimizing these models require significant computational resources and time. If you require a specific Checkpoint or LoRA to be optimized for your hardware constraints, you may submit a formal request and support this ongoing work through the link below:
https://ko-fi.com/morikomorizz
Description
Only Need 8 Steps, Efficient FP8 for Inference.