Untitled:Replicant Model Card

Japanese version is here.

Introduction

Untitled:Replicant is the latent diffusion model made for AI art.

Usage

I recommend to use the model by Web UI. You can download the model here. Then, install Web UI by AUTIMATIC1111. I recommend to use the embeddings.

See also: WD 1.5 Beta 2 - Aesthetic Ver.

Examples

anime, full body, (symmetric), (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed:1.2), a girl in the heaven
Negative prompt: nfixer, nrealfixer, owres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), deleted, old, oldest, ((censored)), ((bad aesthetic)), (mosaic censoring, bar censor, blur censor)
Steps: 60, Sampler: Euler a, CFG scale: 10, Seed: 2843402952, Size: 1024x1024, Model hash: 04be389469, Model: untitledreplicant, Denoising strength: 0.7, Hires upscale: 2, Hires upscaler: Latent

anime, full body, (symmetric), (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed), a humanoid robot
Negative prompt: nfixer, lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), deleted, old, oldest, ((censored)), ((bad aesthetic)), (mosaic censoring, bar censor, blur censor)
Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 20473310, Size: 1024x1024, Model hash: 04be389469, Model: untitledreplicant

anime, full body, (symmetric), (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed), witch, 1girl, lightning, magic
Negative prompt: nfixer, nrealfixer, lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), deleted, old, oldest, ((censored)), ((bad aesthetic)), (mosaic censoring, bar censor, blur censor)
Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 2960555156, Size: 768x768, Model hash: 04be389469, Model: untitledreplicant, Denoising strength: 0.7, Hires upscale: 2, Hires upscaler: Latent

anime, upper body, (symmetric), (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed:1.2), a girl sitting in the cafe
Negative prompt: nfixer, lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), deleted, old, oldest, ((censored)), ((bad aesthetic)), (mosaic censoring, bar censor, blur censor)
Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 1954012709, Size: 768x1024, Model hash: 04be389469, Model: untitledreplicant

anime, full body, (symmetric), (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed), waifu, a girl, solo, ((good pupil)), orange background, simple background
Negative prompt: lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), deleted, old, oldest, ((censored)), ((bad aesthetic)), (mosaic censoring, bar censor, blur censor)
Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 4050907053, Size: 1024x1024, Model hash: 04be389469, Model: untitledreplicant, Denoising strength: 0.7, Hires upscale: 2, Hires upscaler: Latent

anime, upper body, (symmetric), (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed:1.2), replicant, 1girl
Negative prompt: nfixer, nrealfixer, lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), deleted, old, oldest, ((censored)), ((bad aesthetic)), (mosaic censoring, bar censor, blur censor)
Steps: 60, Sampler: Euler a, CFG scale: 10, Seed: 390258972, Size: 1024x1024, Model hash: 04be389469, Model: untitledreplicant

Model Details

• Developed by: Robin Rombach, Patrick Esser, Alfred Increment

• Model type: Diffusion-based text-to-image generation model

• Language(s): English

• License: CreativeML Open RAIL++-M-NC License, Fair AI Public License 1.0-SD

• Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses a fixed, pretrained text encoder (OpenCLIP-ViT/H).

• Resources for more information: GitHub Repository.

• Cite as:

  @InProceedings{Rombach_2022_CVPR,
      author    = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
      title     = {High-Resolution Image Synthesis With Latent Diffusion Models},
      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      month     = {June},
      year      = {2022},
      pages     = {10684-10695}
  }
  

*This model card was written by: Alfred Increment and is based on the Stable Diffusion v2