import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stablediffusionapi/pony-diffusion-v6-xl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("LyliaEngine/Gwent_Style_v2")
prompt = "score_9, score_8_up, score_7_up, BREAK, gwentstyle, a horned creature sitting in a field, tired, sun rising, (dark fantasy:1.2), soft light, <lora:GwentStyle_v2:0.85>"
image = pipe(prompt).images[0]Gwent_Style_v2
- Prompt
- score_9, score_8_up, score_7_up, BREAK, gwentstyle, a horned creature sitting in a field, tired, sun rising, (dark fantasy:1.2), soft light, <lora:GwentStyle_v2:0.85>
- Negative Prompt
- score 1, score 2, score 3, rating_explicit
Model description
Trained on AutismMix DPO, best strengh is .7-.85. Required trigger word gwentstyle. Recommended the use of rating_safe in positive or rating_explicit in negative.
☕If you want to support me feel free to do so on Ko-Fi :)
⚡️BUZZ FOR BEST IMAGES USING THE LORA ⚡️
Trigger words
You should use gwentstyle to trigger the image generation.
Source
https://civitai.com/models/358145/stylepony-gwent?modelVersionId=400316
Credit
https://civitai.com/user/ZyloO
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 10