Verified: 8 days ago
SafeTensor
Type | |
Stats | 6,525 50.8k 115k |
Generation | Getting Hype |
Reviews | |
Published | Sep 2, 2025 |
Base Model | |
Hash | AutoV2 39D49F3A87 |
168.5k
9.2k
48.5k
License:
Nova Anime XL
Nova Anime XL is Nova Anime: Anime/2.5D/3D checkpoint model for SDXL
Pony version aims to get the similar look as both Nova Anime and Nova Domain
All images on example were created with diffusers with custom png tags
PixAI - IL v4.0 Happy Valentine
PixAI - IL v3.0 Happy New Year
PixAI - IL v2.5 Merry Christmas
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, source_anime, BREAK
Negative Prompts: score_4, score_5, 3d, 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: 4~6
Prompt: masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, {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), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, signature, simple background, conjoined,bad ai-generated
Suggested Resources
Workflows
IL
Discussion
I tested the v11 model and found it doesn't differ much from v10. Perhaps v11 has slightly better poses and anatomy? However, the most noticeable change is in the shading. I prefer v10's shading; v11's is too dark, resulting in a less bright and clean overall image. Aside from this, v11 is marginally superior to v10. But given how subtle the difference is, I'll continue using v10, as its shading style appeals to me more.
I tested the new v11. In terms of saturation, it feels a lot like v8, which I really like. The detailing like v10, maybe even a bit better. It follows prompts very accurately. Earlier I mentioned that v10 sometimes produced images with really low detail — I haven’t seen that issue in v11. Anatomy problems still show up, but less often. Right now v11 feels like the best version (though I still love v8 for its softer rendering style)
couldn't test this early but it seems to be decent, I changed my prompts and settings again because my good god, I suck
still good, as always, thank crody :3
I've tested it for a while and found that your model genuinely outperforms WAI's v15.0. Have you considered incorporating some less common poses in the next update? For example, outstretched_legs, foot_on_table, or training different outfit variations for legacy in-game characters?
Gallery
