Z-Image is here, and it's pretty damn great. Let's make it more NSFW!
Recommended Settings
Steps: 12
CFG: 1.0
Sampler: dpmpp_sde
Scheduler: simple
FP8 Download
For some reason, when you upload multiple formats (BF16 + FP8) on one model, which they now support, they hide the FP8 under the BF16 model group in the side menu...
ComfyUI
Models should be placed in diffusion_models, and uses the official workflow with the Load Diffusion Model loader, and loading the VAE/CLIP models separately. Models named "_AIO" should go in the checkpoints folder, and uses the normal checkpoint loaders.
Description
FAQ
Comments (3)
would love to see someone advertise checkpoints that explicitly -OMIT- any and all SDXL/old synthetic training data (especially the detriment-to-humanity-and-the-arts Pony, and "PoNy rEeaLisM" has become). it's so obvious that barely anyone does this. or i haven't found much of it yet. too bad... stg you'd be so ahead of the curve
A lot of time is spent on old datasets, and it's easy to re-use when you know that the data is good.
That said, that is definitely an outdated style / aesthetic.
thx so much, amazing model.ConvRot? RIP fp8