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.<h3 id="recommended-settings">Recommended Settings</h3><ul><li>Steps: 12</li><li>CFG: 1.0</li><li>Sampler: dpmpp_sde</li><li>Scheduler: simple</li></ul>

Z-Image Turbo NSFW [Photorealistic] [ZiT]

Trained for 246.000 steps on a huge dataset. Special thanks to Alcaitiff for their awesome work! This is only the diffusion model. Does not include CLIP or VAE.

zImageTurboNSFW_20FP8.safetensors

2.0_FP8

7.1_FP8

7.0_BF16

7.1_BF16

7.2_BF16

6.2_BF16

6.1_BF16

6.0_FP8

6.0_FP16

6.0_BF16

5.0_BF16

4.5_BF16

4.5_FP8

4.3_BF16_AIO

4.3_FP8

4.3_BF16

4.0_FP8

4.0_BF16

4.0_BF16_AIO

3.0_FP8

3.0_BF16

3.0_BF16_AIO

2.2_BF16_AIO

2.1_FP8_AIO

2.1_BF16_AIO

2.0_BF16

2.0_BF16_AIO

1.0_FP8

Files with SHA256: dd8c0cf7884739d6a37e0be587f16a1ee6ae4c048c8ba02ac08826efdfadb5b5