Image to Image — Image-to-image editing with Step1X-Edit v2 from StepFun. Reasoning-enhanced modifications through a thinking–editing–reflection loop with MLLM world knowledge for abstract instruction comprehension.

≈ 179.243 kredi/üretim

Ayarlar

Image URLzorunlu

The image URL to generate an image from. Needs to match the dimensions of the mask.

Negative Promptisteğe bağlı

The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).

Seedisteğe bağlı

The same seed and the same prompt given to the same version of the model will output the same image every time.

True CFG scaleisteğe bağlı

The true CFG scale. Controls how closely the model follows the prompt.

Num Inference Stepsisteğe bağlı

The number of inference steps to perform. Recommended: 50.

Enable Thinking Modeisteğe bağlı

Enable thinking mode. Uses multimodal language model knowledge to interpret abstract editing instructions.

Enable Reflection Modeisteğe bağlı

Enable reflection mode. Reviews outputs, corrects unintended changes, and determines when editing is complete.

Enable Safety Checkeristeğe bağlı

If set to true, the safety checker will be enabled.

Output Formatisteğe bağlı

The format of the generated image.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap