Text-to-Image
Diffusers
Safetensors
English
Merge
image-generation
Anime
stable-diffusion-xl
stable-diffusion
noob
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("za4BeqsBV36z2s889/zabramix3", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]zabramix 3
A merge of ChenkinNoob XL V0.2 with a few custom trained style gloras for a more consistent style
|
|
|
|
|
|
|
|
|
|
|
|
See more sample images (log in required for NSFW) at Arc en Ciel
Recommended Settings
- Positive prompt:
masterpiece, best quality - Negative prompt:
worst quality, low quality, lowres, jpeg artifacts, bad anatomy, bad hands, watermark - Steps: 20-30
- CFG Scale: 5-7
- Sampler:
Euler a - Resolution:
832x1216or1216x832or1024x1024 - Adetailer/FaceDetailer to improve face detail
Recommended Models
- Anzhc's Face Segmentation YOLO for Adetailer/FaceDetailer
- Anzhc's SDXL Anime VAE B3 (built into this checkpoint)
- 2x-AnimeSharpV4 upscaler
- Downloads last month
- 6
Model tree for za4BeqsBV36z2s889/zabramix3
Base model
Laxhar/noobai-XL-0.6 Finetuned
Laxhar/noobai-XL-0.75 Finetuned
Laxhar/noobai-XL-0.77 Finetuned
Laxhar/noobai-XL-1.0 Finetuned
Laxhar/noobai-XL-1.1 Finetuned
ChenkinNoob/ChenkinNoob-XL-V0.2