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
Base Version with 30-50 steps
FAQ
Comments (9)
testing the model, i well say its really good and fast if you compare it to turbo version even, with 15 steps still faster than tubro, but its only Asian people i hope to get release with different races, thanks man
Thank you for the appreciation. next, I will try to integrate several LoRas to achieve slightly better results.
How can I get the workflow for this checkpoint?
wait, i will upload the example workflow
Your workflow doesn't work.. zimage-dit-merged.safetensors? I can't find it.. Sorry!
Sorry about that, you can change the zimage-dit with the checkpoint of this model.
???
@choe0ho821
Sorry for the confusion. The workflow is just an example template. To make it work, you just need use my model
1. download the model file (.safetensors) from this page.
2. put the downloaded file into your ComfyUI/models/checkpoints folder.
3. refresh or restart the comfyui
4. In the workflow, find the 'Load Checkpoint' node, click on the model name, and change it from 'zimage-dit-merged.safetensors' to the model you just downloaded.
It should work perfectly, It seems you might have forgotten to put the downloaded model file into your ComfyUI folder.
@MorikoMorizz workflow fixed atleast for me, i'm running your V2 model.