Sign In

RE:SONATE

141
843
9
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
469
Reviews
Published
Dec 22, 2023
Base Model
SD 1.5
Hash
AutoV2
70D2BA1B8E
default creator card background decoration
Failed Generation Contest Participant
AI_AIDIA's Avatar
AI_AIDIA

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 help 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.

The third model of the series, I present to you "RE:SONATE".

This is a 2D model that generates beautiful characters with great fashion style. I use this model to create many street snaps, it is able to create detailed outfits with dynamic shading on the character, while maintaining high quality (and sometimes semi-realistic) background with depth. This model does not have any biases color tone, it is flexible between vibrant color and realistic shadings. As usual, hands are not my strong point, please inpaint if needed.

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

VERSION:

ORIGINAL VERSION - The main RE:SONATE model, 3.97GB.
LITE VERSION - Pruned down to 1.99GB, seems like no changes to result.

RE:COLLECTION Model Series:

  1. RE:QUIEM - 2.5D Stylized Model

  2. RE:LIVE - 2D Vibrant Atmosphere Model

  3. RE:SONATE - 2D Character Focus Model

  4. RE:VOLUTION - 2D High-detail Model

  5. RE:IMAGINATION - 2D Art Stylized Model

  6. RE:LAXATION- 2D/2.5D Simple & Clean Model

  7. RE:KINDLE- 2D Soft Bishoujo 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), (superman logo:1.5), watermarks, signature


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.