Stable Diffusion with 6 fixed category
Lazy version of Stabel Diffusion with Civitai. Generate images with rough 6 category. Free you from choosing model in civitai. You can freely control parameters such as prompt, size, etc
Try it in the Widget Center
Click this url to try this widget and copy the Pro Config template.
Usage
Feeling too lazy to pick a model ID from Civitai? Give our pre-selected SD&LORAS a try. Effortless version of Stable Diffusion with Civitai. Produce images across approximately 6 categories. Eliminates the need to select a model in Civitai. You have the freedom to adjust parameters like prompt, size, and more.
Input Parameters
category
string
Lazy to choose model id from civitai? try use our pre-picked sd&loras
Realistic & Photorealistic
prompt
string
The text prompt for image generation. Add lora? add `` to your prompt. `$id` is the series number and `$weight` is the lora weight you want (always set to 1.0). You can use multiple loras.
negative_prompt
string
The negative prompt for image generation.
(worst quality, low quality:1.4),(malformed hands:1.4),(poorly drawn hands:1.4),(mutated fingers:1.4),(extra limbs:1.35),(poorly drawn face:1.4),bad leg,strange leg, poor eyes, full screen of face
sampler
string
Sampler for diffusion model inference
DPM++ 2M Karras
height
integer
Height of the generated images
512
width
integer
Width of the generated images
512
steps
integer
Steps for sampler to step whle sampling
25
cfg_scale
number
Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results. Default to 7.
7.0
seed
integer
Random seed for generation process. -1 means random seed
-1
clip_skip
integer
Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.
1
enable_hr
boolean
Enable the post-process high resolution. If it is set to false, please ignore the parameter with prefix `hr_`
False
hr_scale
integer
Improve the image quality by enlarging it in a way while maintains the original ratios. Default to 2. If `hr_height` or `hr_width` is set to a value other than zero, this parameter will not be applied.
2
hr_upscaler
string
The super resolution model used
ESRGAN_4x
hr_resize_x
integer
Resize width to, 0 means not defined. If x set to 0, and y is not 0, we will resize the length of image to y and change width accordingly. If x and y both not zero, use the max ratio max(hr_resize_x/image.width, hr_resize_y/image.height)
0
hr_resize_y
integer
Resize height to, 0 means not defined. If y set to 0, and x is not 0, we will resize the width of image to x and change width accordingly. If x and y both not zero, use the max ratio max(hr_resize_x/image.width, hr_resize_y/image.height)
0
hr_second_pass_steps
integer
Steps of sampling for second pass of diffusion model after hires. Set to 0 means the same steps as first pass.
0
hr_denoising_strength
number
Strength of image transfomation during hires transform. High means more influence during second pass sampling after hires
0.7
Output Parameters
url
string
The url of generated image, stored in the cloud. Only temporarily effective, will be cleared in a few hours.
image
Output Example
Detailed Guidelines
Unique Parameter:
category: Feeling too lazy to pick a model ID from Civitai? Give our pre-selected SD&LORAS a try.Choose from
["Anime", "Realistic & Photorealistic", "Landscape", "Fantasy & Illustration", "3D & Cartoon", "Cute & Fantasy Characters"]
Last updated