qwen/qwen-image

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.

Input

Configure the inputs for the AI model.

Seed

Random seed. Set for reproducible generation

Image

Input image for img2img pipeline

Prompt *

Prompt for generated image

Go Fast

Enable

Run faster predictions with additional optimizations.

Guidance

Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5

Strength

Strength for img2img pipeline

image_size

Image size for the generated image

Lora Scale

100

Determines how strongly the main LoRA should be applied.

aspect_ratio

Aspect ratio for the generated image

Lora Weights

Load LoRA weights. Only works with text to image pipeline. Supports arbitrary .safetensors URLs, tar files, and zip files from the Internet (for example, 'https://huggingface.co/Viktor1717/scandinavian-interior-style1/resolve/main/my_first_flux_lora_v1.safetensors', 'https://example.com/lora_weights.tar.gz', or 'https://example.com/lora_weights.zip')

output_format

Format of the output images

Enhance Prompt

Enhance the prompt with positive magic.

Output Quality

100

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Negative Prompt

Negative prompt for generated image

Replicate Weights

Load LoRA weights from Replicate training. Only works with text to image pipeline. Supports arbitrary .safetensors URLs, tar files, and zip files from the Internet.

Num Inference Steps

Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Disable Safety Checker

Enable

Disable safety checker for generated images.

Output

The generated output will appear here.

No output yet

Click "Generate" to create an output.