Everyjourney

A Stable Diffusion 1.5 model that has been trained on 503 image generated from Niji*Journey.
The current model is finetuned with 2.0e-6 learning rate, 154.000 training steps.
Dataset has been preprocessed using Aspect Ratio Bucketing Tool.
I have utilized BLIP2 as a part of the training process as natural language prompts might be more effective.
This checkpoint model can generate 2D to 2.5D images (by just adding realistic or photorealistic prompt)

Model Details

Trained and Maintained by: Gorilla Monsoon III
Model type: Stable Diffusion 1.x Model
Model type: This is a model that can be used to generate and modify images based on text prompts.
License: CreativeML Open RAIL++-M License

Update

04/07/2023: Added Baked with VAE version
05/07/2023: Added 3 Merged Models (affogato, gelato, tiramisu)
affogato: everyjourney x 0.25 + anemone-V1 x 0.25 + eclipse-V1Asami x 0.5
gelato: everyjourney x 0.4 + animefull-final-pruned-fp16 x 0.3 + AnythingV5_v5PrtRE x 0.3
tiramisu: everyjourney x 0.25 + AOM x 0.3 + meinamix x 0.3

How to Use

Enable CLIP Changer extension on A1111 SD Webui
Set CLIPTextModel and CLIPTokenizer to: openai/clip-vit-large-patch14
Download and select this model as checkpoint
Default VAE for this model is this
Default CLIP skip:1

Sample Images

2D Sample
2.5D Sample
Merged Model Sample
affogato
gelato
tiramisu

Prompt and settings for Samples

(illustration), a beautiful woman standing outdoors, depth of field, elegance, drill hair, twin drills, (blush:0.7), floating hair, petals, shining, movie poster, (colorful:1.1), hair ornament, petals, (pantyhose:1.1), ribbon, shaded face  

Negative prompt: easynegative 

Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 591108620, Size: 512x768, Model hash: 2d9122ee83, Model: everyjourney, Denoising strength: 0.7, Token merging ratio: 0.5, Token merging ratio hr: 0.5, Hires upscale: 2, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B

2.5D

RAW,photorealistic, best lighting, complex pupils, detailed background, dusk, woman, solo, upper body, (close up, face focus:1.2), looking up, cowboy shot, standing, bashful, shiny skin, eyeliner, gothic eyeshadow, blush, flower, long hair, curly hair, titian hair, highly detailed skin,  

Negative prompt: easynegative  

Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3667144738, Size: 512x768, Model hash: 2d9122ee83, Model: everyjourney, Denoising strength: 0.7, Token merging ratio: 0.5, Token merging ratio hr: 0.5, Hires upscale: 2, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B

License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

You can't use the model to deliberately produce nor share illegal or harmful outputs or content
The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license. Please read the full license here