Z-Image version is available!
Nova Reality
Nova Reality is realistic SDXL checkpoint with great feels of details
All images on example were created with diffusers with custom png tags
Rules
You cannot use the generated images for commercial use if it's not edited (or just turning it to black and white)
You can share images without any restriction if you don't monetize it
Advertising this model to outside is always welcome
Recommend Settings
Sampler: Euler a
Steps: 20~30
Clip Skip: 1-2
Denoising Strength: 0.65 - 0.8
(Pony)
CFG Scale: 5~7
Prompt: score_9, score_8_up, score_7_up, realistic, photo, detailed face, detailed skin, BREAK
Negative Prompts: score_6, score_5, score_4, score_6_up, score_5_up, score_4_up, source_anime, source_furry, source_pony, source_cartoon, blurry, jpeg artifacts, normal quality, worst quality, low quality, missing fingers, extra digits, fewer digits, bad eye
(Illustrious)
CFG Scale: 4-6
Prompt: masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, scenery, photorealistic, {Prompt}, BREAK, depth of field, photorealistic details
Negative Prompts: modern, old, oldest, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digits, fewer digits, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated
Description
Initial version for Illustrious with similar look and better realism
FAQ
Comments (14)
For the Illustrious ver what base model you used?
Based on Noob epred1.1+vpred1.0, most structures are from CyberIllustrious and IllustriousSat Real
great realism model. follows prompts, results look nice. good job!
Illustrious v1 has interesting sensitivity to CFG. Even changes of 0.1 in either direction can drastically affect composition and quality. Generally temperamental, see my review for more details. Pretty fun though.
Love this model, needs a detailed prompt but delivers correct response! Great Job! Thx
Needs on-site generator.
might be the best model yet
What would be the notable advancement with Illust V1?
Pose, composition and prompt adherence
@Crody Are there any plans to make an Asian version of this one?
@a4846716863 Already made
literally in the description