metadata
license: creativeml-openrail-m
language:
- en
- pt
tags:
- text-to-image
- stable-diffusion-xl
- diffusers
- imageflow
base_model: stabilityai/stable-diffusion-xl-base-1.0
pipeline_tag: text-to-image
🌊 Imageflow.1.1.1
Text-to-Image model by jeffvedd
Base: stabilityai/stable-diffusion-xl-base-1.0
Framework: 🤗 Diffusers
🚀 Uso Rápido
from diffusers import StableDiffusionXLPipeline
import torch
pipe = StableDiffusionXLPipeline.from_pretrained(
'jeffvedd/Imageflow',
torch_dtype=torch.float16,
use_safetensors=True,
).to('cuda')
image = pipe(
prompt='A futuristic city at night, neon lights, ultra detailed',
negative_prompt='blurry, low quality',
num_inference_steps=30,
guidance_scale=7.5,
).images[0]
image.save('output.png')
⚙️ Parâmetros Recomendados
| Parâmetro | Valor |
|---|---|
guidance_scale |
7.0 – 9.0 |
num_inference_steps |
25 – 40 |
resolution |
1024×1024 |
Autor: jeffvedd · Treinado em: Kaggle GPU