NOTE: Civit has made the download UI confusing. For the v4.0 model, it contains four versions:
BF16 UNET (11GB)
FP8 UNET (6GB)
Q6 GGUF UNET (5GB)
FP8 Checkpoint (16GB)
I uploaded them very descriptively but Civit has stripped away the descriptions so it's now confusing to see what you're downloading. The FP8 checkpoint is an all-in-one version that contains the VAE and Text Encoder. For the UNETs you need to provide those extra models.
I've used 100s of curated images to help add some better color, contrast and detail to the Z-Image Turbo model. It's not a huge difference yet, but it is noticeably better in side by side tests. I'm starting out a bit conservative because I don't want to mess up any of the great compositional features that Z-Image offers.
Use the workflow embedded in the showcase images for the model version to get the best results. Check the About this version section for links to the workflow and recommended settings. Z-Image currently mangles nipples and genitalia so my workflow uses SDXL detailers to refine just those aspects of the image.
P.S. I would appreciate any constructive feedback on how to make this model better.
Description
V1.0 BF16 converted to FP8 E4M3FN.
FAQ
Comments (5)
For those who prefer very slim ladies (or even very heavy ones), there's now a great LoRa:
https://civitai.com/models/2210034
Can't say that any Z-Image merges are very convincing yet, but this one at least looks like a small improvement and seems to work well with the lora's I've made
Thanks, it was my intention with this first version to just make it a small improvement in color/detail over the official z-image. Future versions should be much better.
Thank you so much your work is the best.