Sign In


Checkpoint Merge
May 18, 2024
Base Model
SD 1.5
default creator card background decoration
Legendary Landscape Contest Participant
AI_AIDIA's Avatar

Welcome to my RE:COLLECTION.

I am exploring every possibility I can do in this passionate hobby of mine. I am still slow to learn, if there is anything I am not doing enough, I would love to get your advice and feedback (I am not very IT savvy). If you want to share any of my model on other sites, I am happy to let you do it as long as it is not for monetization, but please inform me as I may already have account on some sites.

My second model "RE:LIVE", it was mixed around to create a more anime focus style model as compared to my prior model.

This is a anime model that generates 2D anime characters with very atmospheric lighting and shadings, often having softer colored lines. This model is able to bring a vibrant range of colors with a hint of cool undertones. This model is more of an experiment work with anime style, so I expect more unstable generation to happen, especially with the hands. please use in-paint if you need to fix it.

I do not do NSFW test with my model, if they appear unintentionally, just add "NSFW" in the negative prompt.

Switch between version to compare the difference.
Image comparison range: Image 2 to Image 13


ORIGINAL VERSION - The main RE:LIVE model, 5.55GB.
LITE VERSION - Pruned down to 1.99GB, there will be small changes to result.
VIVID PAST VERSION - This version can generate bright and lively images.
[NEW] VIVID PAST VERSION - This version can generate bright but dark and cool images.


  1. RE:QUIEM - 2.5D Stylized Model

  2. RE:LIVE - Anime Atmospheric Model

  3. RE:SONATE - Anime Character Focus Model

  4. RE:VOLUTION - Anime High Detail Model

  5. RE:IMAGINATION - 2D Stylized Model

  6. RE:LAXATION- 2D/2.5D Gentle Model

  7. RE:KINDLE- Soft Shoujo Model

*From the 5th model(RE:IMGAGINATION) onwards, I've not test the LITE model, result between the full and pruned version may slightly vary. All showcase are generated with the full version.

Please try around with your settings, but if you need a guide, this is my settings:

---Generation Setting---
Sampling Steps: 30
Sampling Method: DPM++ 2M Karras
CFG scale: 7
Clip skip: 1 or 2
SD VAE: kl-f8-anime2.ckpt

---Hires. fix---
Denoising strength: 0.5
Hires upscale: 2 ~ 2.5
Hires steps: 15
Hires upscaler: 4x-UltraSharp

There isn't any fixed prompt, but I can recommend to try these:

Positive Prompt: best quality, masterpiece, absurbres, super-resolution

Negative Prompt: badhandv4, easynegative, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (worst quality, low quality:1.4),text, words, logo, watermark

Disclaimer: I do not bake my models with VAEs or embedding as some will prefer to use their own, if you want my result, just follow my setting and prompts.