<p>Z-Image is here, and it's pretty damn great. Let's make it more NSFW!</p><h3 id="recommended-settings">Recommended Settings</h3><ul><li><p>Steps: 12</p></li><li><p>CFG: 1.0</p></li><li><p>Sampler: dpmpp_sde</p></li><li><p>Scheduler: simple</p></li></ul><h3 id="fp8-download">FP8 Download</h3><p>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...</p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9cc7e493-abe7-4852-b947-8c55793f4ca6/original=true/9cc7e493-abe7-4852-b947-8c55793f4ca6.jpeg" /></p><h3 id="comfyui">ComfyUI</h3><p>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.</p>

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 an AIO Checkpoint version. CLIP and VAE are included.

zImageTurboNSFW_21FP8AIO.safetensors

2.1_FP8_AIO

8.2 (BF16+FP8)

8.0_BF16

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_BF16_AIO

2.0_FP8

2.0_BF16

2.0_BF16_AIO

1.0_FP8

Files with SHA256: 7fdfafda0690451129cfc7608c62768e5aee5d0cf27feaf0bb34e2622b0a9f35