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
Retouch visuals
NoobAI EPS v1.1 + Illustrious v1.1 DARE applied
FAQ
Comments (7)
Results get a bit funky if using anything but Euler A, but within these constraints, the new 3.0 is pretty damn great.
Surprisingly good prompt adherence for a photorealistic illustrious model.
does novareality3.0 support the vpred from noobai? cause i am trying to generate low light images and none of them are coming out dark i keep getting lights
The model is in epred so it doesn’t support for v-pred
the whole model has a yellow tint, even if i use pale skin. the female skin is till orange/yellow
I'm a complete noob at AI image generation, and after watching a five-minute video on ComfyUI and downloading several models, this one is by far the best to create excellent images with a rudimentary setup and understanding. My only complaint is that it does not seem very good at creating any race besides white. It will not create Asian girls at all. Even the Asian version of this model only creates white girls with vaguely Asian-looking eyes. Other than that, a great model for a total beginner.
.... just use loras
If you're new then get used to seeing tha face everywhere. I'm surprised you hadn't noticed it before as it's the default face and found everywhere in AI generated content.
Details
Files
novaRealityXL_illustriousV30.safetensors
Mirrors
novaRealityXL_illustriousV30.safetensors
novaRealityXL_illustriousV30.safetensors
novaRealityXL_illustriousV30.safetensors
novaRealityXL_illustriousV30.safetensors
NovaRealityILV3.safetensors
novaRealityXL_illustriousV30.safetensors
novaRealityXL_illustriousV30.safetensors
novaRealityXL_illustriousV30.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.