dezgo.com Open in urlscan Pro
2606:4700:3037::6815:1eb1  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Text-to-image



   FREE

DEZGO

Login

--------------------------------------------------------------------------------

Text-to-Image XL

--------------------------------------------------------------------------------

Text-to-Image
Controlled Text-to-Image
Image-to-Image
Upscale
Inpainting from text
Edit image from text
Remove background
Text-to-video [BETA]

--------------------------------------------------------------------------------

FAQ / Support
Models
API
Twitter
Discord
System Status
Affiliate
powered by Stable Diffusion AI
Terms - Privacy - Open RAIL-M License
- New feature "background removal": easily remove backgrounds from your images
with just one click. Available as a standalone function & as an option on XL
models. Try it!
- New XL model "Tshirt Design Redmond": unleash your creativity and generate
stunning t-shirt designs. Available in both Free & Power Mode. Try it!
- New "Shop" Button: Loved an image? Now you can directly order custom prints on
a variety of products like t-shirts, mugs, and more.


GENERATE AN IMAGE FROM A TEXT DESCRIPTION

POWERED BY STABLE DIFFUSION AI (CREATIVEML OPEN RAIL-M)

Prompt

Describe how the final image should look like


Model

The AI used to generate the image.
DreamShaper 8 (general)




Available in Power Mode

Count

Number of images to generate

More options

LoRA

Choose extension models
Setup LoRA (0 enabled)

Resolution

Choose image resolution

Portrait





Square





Landscape


Width

Height

Negative prompt

Describe what you DON'T want in the generated image
ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of
frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad
anatomy, blurred, watermark, grainy, signature, cut off, draft


Guidance

Adjusts how much the AI tries to fit the prompt (higher = stricter, lower = more
freedom). The sweet spot is between 6-10, extreme values may produce more
artifacts.

7



Available in Power Mode

Steps

Number of sampling steps. More steps = more details but also longer computation
time.


Sampler

Defines the sampling method used to generate the image.
DPM++ 2M Karras




Seed

Unique image seed number. If not provided, the image will be random.


Available in Power Mode

Upscale

Upscale the image by this factor using the Real-ESRGAN model. Currently only a
factor of 2 is supported.


Run




An error has occurred. This application may need to be reloaded. Reload Dismiss