Instructions to use ddcu3eij/zxcv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ddcu3eij/zxcv with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("natsusakiyomi/SakuraMix", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ddcu3eij/zxcv") prompt = "zxcvv" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
zxcvv

- Prompt
- zxcvv
- Negative Prompt
- ribs,text,watermark,negative_hand-neg,mutated hands,extra limbs,multiple views,ng_deepnegative_v1_75t,verybadimagenegative_v1.3,(blurry:1.3),(lowres:1.1),error

- Prompt
- zxcvv
- Negative Prompt
- ribs,text,watermark,negative_hand-neg,mutated hands,extra limbs,multiple views,ng_deepnegative_v1_75t,verybadimagenegative_v1.3,(blurry:1.3),(lowres:1.1),error

- Prompt
- zxcvv
- Negative Prompt
- ribs,text,watermark,negative_hand-neg,mutated hands,extra limbs,multiple views,ng_deepnegative_v1_75t,verybadimagenegative_v1.3,(blurry:1.3),(lowres:1.1),error

- Prompt
- zxcvv
- Negative Prompt
- ribs,text,watermark,negative_hand-neg,mutated hands,extra limbs,multiple views,ng_deepnegative_v1_75t,verybadimagenegative_v1.3,(blurry:1.3),(lowres:1.1),error

- Prompt
- zxcvv
- Negative Prompt
- ribs,text,watermark,negative_hand-neg,mutated hands,extra limbs,multiple views,ng_deepnegative_v1_75t,verybadimagenegative_v1.3,(blurry:1.3),(lowres:1.1),error

- Prompt
- zxcvv
- Negative Prompt
- ribs,text,watermark,negative_hand-neg,mutated hands,extra limbs,multiple views,ng_deepnegative_v1_75t,verybadimagenegative_v1.3,(blurry:1.3),(lowres:1.1),error

- Prompt
- zxcvv
- Negative Prompt
- ribs,text,watermark,negative_hand-neg,mutated hands,extra limbs,multiple views,ng_deepnegative_v1_75t,verybadimagenegative_v1.3,(blurry:1.3),(lowres:1.1),error
Model description
zxcvb - pixiv rkgk style, trained on 6000 images, 1 epoch
zxcvv - smug face style, trained on 230 images, 5 epoch
use weight 0.5 - 0.6
Trigger words
You should use zxcvb to trigger the image generation.
You should use zxcvv to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 8
Model tree for ddcu3eij/zxcv
Base model
natsusakiyomi/SakuraMix