Image to Image · Text to Image — HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

≈ 44.811 kredi/görsel

Ayarlar

Image URLzorunlu

The image URL to generate an image from.

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).

Image Sizeisteğe bağlı

The size of the generated image. Setting to None uses the input image's size.

Num Inference Stepsisteğe bağlı

The number of inference steps to perform.

Seedisteğe bağlı

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

Guidance scaleisteğe bağlı

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

Num Imagesisteğe bağlı

The number of images to generate.

Enable Safety Checkeristeğe bağlı

If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.

Output Formatisteğe bağlı

The format of the generated image.

Lorasisteğe bağlı

A list of LoRAs to apply to the model. Each LoRA specifies its path, scale, and optional weight name.

Strengthisteğe bağlı

Denoising strength for image-to-image generation.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap