This is a version of <a target="_blank" rel="ugc" href="https://civarchive.com/models/133005/juggernaut-xl">Juggernaut XL</a> that has been merged with the base SDXL inpainting model. This results in much more cohesive and higher quality inpainting results compared to normal Juggernaut XL model. It's much better at hiding the seam between generated and original content.<a target="_blank" rel="ugc" href="https://civarchive.com/models/403361?modelVersionId=456538">Click here for older versions of JXL inpainting</a>

Juggernaut XL Inpainting (Updated)

Inpainting version of Juggernaut XL version XI. Includes FP16 VAE fix."The whole Juggernaut 9 Dataset recaptioned and trained for XI (15k Images)Res: 832*1216 (For Portrait, but any SDXL Res will work fine)Sampler: DPM++ 2M SDESteps: 30-40CFG: 3-6 (less is a bit more realistic)Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image. I don´t recommend using my Negative Prompt, i simply use it because i am lazy :DVAE is already Baked InHiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale"-Juggernaut XL version XI

Files with SHA256: 0ceb0a3dab75f7bb9d9f1f19045e347fd78df64153d6c89166386111b22695bb