Z-Image is here, and it's pretty damn great. Let's make it more NSFW!
Still a work in progress. It can output good genitals, but not always. About 3/5 images are good, working on penis stability specifically for future versions.
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.
Recommended Settings
Steps: 12
CFG: 1.0
Sampler: dpmpp_sde
Scheduler: simple
Description
Trained for 46.000 steps on a huge dataset.
Special thanks to Alcaitiff for their awesome work!
Place this version in the diffusion_models folder.
FAQ
Comments (13)
pretty good, but doesn´t work well with LORA ... :-( ... any chance for a fp16 version?
Yeah, it does not match well with other LoRAs, they eat each other up. I'm not sure how to solve this. It may not be possible with the current method we are training ZiT.
FP16 version coming.
I was same via lora
Can't say I dislike this model, its fairly interesting, I would even call it POV ZIT as it specializes in POV view
Didn't consider that, maybe there's too much PoV in the training data if it has a bias towards this. Good catch.
Even after adding LoRA, it still generates speckled images. The LoRA was trained on this website.
Yeah LoRAs are not working well here. Hoping to fix in future versions.
@6tZ Does this model have special requirements for text encoders and VAEs? I directly used the invoice and the UI generated based on the official version of Z-Image that I modified myself, without adding Lora, both is still a black and white speckle image, like a QR code
@leewheel456 hmm, no special requirements. Version 1 should be placed in diffusion_models, and uses the official workflow. Version 2 and forward are checkpoints, so you use the normal checkpoint loaders.
Having trouble getting LoRAs to work with this model?
Before you give up, try ModelMergeSimple.
It’s a ComfyUI node, and it often fixes LoRA compatibility issues instantly.
How to use it:
Connect two Checkpoint Loaders, two UNet Loaders, or one Checkpoint + one UNet
Feed them into ModelMergeSimple
Then connect the output to your LoRA loaders
If that still doesn’t solve it, try this proven combo:
Model Loader #1: a model you know already works well with LoRAs > Connect with lora model loaders.
Model Loader #2: this NSFW model
Merge both using ModelMergeSimple
After that, your LoRAs should behave normally,
instead of looking like they were generated by a sleep-deprived potato 🥔😄.
If this works, smash that like button out of pure gratitude 😄
If it doesn’t work… like it anyway... for emotional support, moral victory, and because you already read this far 😌👍(lol).
As long as you use a proper LoRA loader with support for ZiT it should work.
The official one supports it properly now I think.
It doesnt work and shows an error message: AttributeError: 'Linear' object has no attribute 'weight_scale'
@fsh101686 Can you post a link of the lora that does not work with this checkpoint. i will test it out myself and see if i can get it working