Japanese review for this model by nobin
Nova 3DCG XL
Nova 3DCG is sdxl checkpoint that has similar looks of Nova Anime XL and having 3d strcture that almost looks like PVC Figures or certain 3D models
Which can be described as Nova Doll Pony
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, score_6_up, score_5_up, score_4_up, BREAK
Negative Prompts: score_4, score_5, jpeg artifacts, username, watermark, signature, normal quality, worst quality, large head, low quality, text, error, missing fingers, extra digits, fewer digits, bad eye
(Illustrious)
CFG Scale: 3-5
Prompt: masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, 3D, rendered, {Prompt}, BREAK, depth of field, volumetric lighting
Negative Prompts: modern, recent, 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, cropped, very displeasing, (worst quality, bad quality:1.2), sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated
Description
Increased details and prompt adherence
NoobAI EPS v1.1 + Illustrious v2.0 stable DARE applied
FAQ
Comments (14)
Seriously impressive stuff!
This is my favorite 3D model. It's so good.
Does this use Illustrious/Noob/Pony LORAs?
For Illustrious versions, you can use both Illustrious and Noob LoRAs
No LoRAs were used in merge for the latest version
This is easily my new favorite model
I'm genuinely impressed by this model. I've been using primarily NoobAI, and this model seems to put out consistent and quality details like teeth and fluids at a higher rate than NoobAI. The only downside is that at seemingly random times, I will add a tag to the prompt and the result will be pure noise. But if I tweak the prompt slightly it will go back to generating images normally. Not a big deal but I'm not sure why it happens.
Most cases it’s because of SDXL prompt calculation
It uses this calculation on top of SD1.5 calculation
z = z * (original_mean / new_mean)
Because of that, when the either new_mean or original_mean goes negative, the whole thing goes negative as well and you get noises
To prevent this, don't use the tag and instead try finding alternative words that make the same meaning
Crody Ok, thanks for the tip.
Been using stable diffusion for 3 or 4 years now this is my new favorite model by far
yes
Very good at making semi-realistic CGI looking pictures.
What's going to be the difference between this and Nova Anime 3DXL? They're starting to converge in style.
3DCG focuses on Blender / CG looks thus results in more western feel
Anime3D focuses on Gacha looks which has more easten feel
Crody Yeah I did a test on both with various loras/prompts. The eyes are the biggest giveaway. Thanks for the confirmation!
Details
Files
nova3DCGXL_illustriousV40.safetensors
Mirrors
nova3DCGXL_illustriousV40.safetensors
Nova3DCGILV4.safetensors
nova3DCGXL_illustriousV40.safetensors
nova3DCGXL_illustriousV40.safetensors
nova3DCGXL_illustriousV40.safetensors
nova3DCGXL_illustriousV40.safetensors
nova3DCGXL_illustriousV40.safetensors
nova3DCGXL_illustriousV40.safetensors
nova3DCGXL_illustriousV40.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.