Cancel
Save as New
by
Add an image and a prompt and this workflow will alter the image using your text & the latest Stable Difussion Img2Img AI model.
Run
Examples
API
3y ago
Describe your edits
⚙️ Settings
Dreamlike Photoreal 2.0 (dreamlike.art)
Nano Banana Pro (Google)
Nano Banana 2 (Google)
Nano Banana (Google)
FLUX.1 Pro Kontext (fal.ai)
GPT Image 2 (OpenAI)
GPT Image 1.5 (OpenAI)
✨ InstructPix2Pix (Tim Brooks)
DreamShaper (Lykon)
Stable Diffusion v2.1 (stability.ai)
Stable Diffusion v1.5 (RunwayML)
Search for our available models here to learn more about them.Please use our default settings for optimal results if you're a beginner.
Control Net models provide a layer of refinement to the image generation process that blends the prompt with the control image. Choose your preferred models:
Human Pose | Tiling
Canny
Depth
HED Boundary
M-LSD Straight Line
Normal Map
Human Pose
Scribble
Image Segmentation
Tiling
Brightness
QR Monster V2
At 0 the prompted visual will remain intact, regardless of the control nets.
At 0 the prompted visual will remain intact, regardless of the control nets
At 2 the control nets will be applied tightly to the prompted visual, possibly overriding the prompt.
At 2 the control nets will be applied tightly to the prompted visual, possibly overriding the prompt
Human pose estimation.
Tiling: to preserve small details.
This allows you to specify what you DON'T want to see in your output.Useful negative prompts can be found here.
Image generation engines can often generate disproportionate body parts, extra limbs or fingers, strange textures etc. Use negative prompting to avoid disfiguration or for creative outputs like avoiding certain colour schemes, elements or styles.
Change the number of outputs for a single run here:
By default, each run produces one output per Model.
How precise, or focused do you want your output to be?
An increase in output quality is comparable to a gradual progression in any drawing process that begins with a draft version and ends with a finished product.
(Text Guidance Scale) How pressurized should the AI feel to produce what you want?How much creative freedom do you want the AI to have when interpreting your prompt?
At lower values the image will effectively be random. The standard value is between 6-8. Values that are too high can also distort the image.
Run cost = 5 credits
With each run, you agree to Gooey.AI's terms & privacy policy.
Download
Regenerate
🐞 Debug
🙋🏽♀️ Need more help? Join our Discord
Generate AI-empowered artistic QR codes tailored to your style for impactful marketing, branding & more with Gooey.AI. Add your URL and image prompt, we'll create in an AI QR code in under 30 seconds. Check …
Generate stunning AI images of yourself and boost your confidence on social media. Great for turning your selfies into wacky AI portraits. It’s perfect for those who want to save money on professional …
Create multiple AI images from a single prompt! Describe what you want to see in the text box. Select AI models to compare (OpenAI, Stability.AI, DALL-E, etc.). Tap "Run" to generate images on the right …