Verified: 5 months ago
SafeTensor
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
适用于各种游戏画面的ai文生图和图生图
适用于各种画面的欧美休闲风格画风转换
lora权重控制在0.45-0.85之间，0.75最为稳定
迭代步数：30步
采样方法：Euler或Euler a
高清修复：放大算法R-ESRGAN 4x+ Anime6B
放大倍数1.5~2之间
提示词引导系数：8
在线使用 ， 如需源文件可+V jingxiang011101
如果清晰度不够请开高放大倍数或者调分辨率，要想转变原有的画风并且保持细节不变，可通过图生图重回幅度调整成0.4~0.6之间，通过不断套娃换底图进行画风转换
AI Wenshengtu and Tushengtu for various game screens
European and American casual style painting style conversion for various screens
Lora weight is controlled between 0.45-0.85, 0.75 is the most stable
Iteration steps: 30 steps
Sampling method: Euler or Euler a
HD restoration: enlargement algorithm R-ESRGAN 4x+ Anime6B
Enlargement factor between 1.5 and 2
Prompt word guidance coefficient: 8
Online use, if you need the source file, you can +V jingxiang011101
If the clarity is not enough, please increase the magnification or adjust the resolution. If you want to change the original style and keep the details unchanged, you can adjust the amplitude of the picture to between 0.4 and 0.6 through the picture, and change the style by constantly changing the base map.