Image generation
Based on text only
Image can be generated based on text prompt in given resolution.
And the result:
There are additional positive and negative prompts by default:
Field name | Default value |
---|---|
additional_prompt | high quality, highly detailed, 8K |
negative_prompt | lowres, bad anatomy, bad hands, worst quality, bad proportions, blurry, cloned face, cropped, deformed, dehydrated, disfigured, error, extra arms, extra fingers, extra legs, extra limbs, fused fingers, gross proportions, jpeg artifacts, long neck, low quality, lowres, malformed limbs, missing arms, missing legs, morbid, mutated hands, mutation, mutilated, out of frame, poorly drawn face, poorly drawn hands, signature, text, too many fingers, ugly, username, watermark, worst quality, deformed architecture, deformed furniture, extra table legs, extra chair legs, doubled |
They can be overwritten by:
Based on image
Images can be generated based on face details or image canny edges.
Field name | Description |
---|---|
adapter_type | This parameter controls how generator will use the input image.
|
face_id | true/false - Works only when adapter_type is face. Selects different face generation algorithm when just face details are used (skips for example hair style from original photo). |
controlnet_conditioning_scale | Float value from 0 to 1 describes how much edges will be preserved. Default value is 0.5 |
Let's check some examples.
And the result
And the result
And the result
Generative upscaling
Let's try to use generative upscaling. This algorithm can do some real magic 🙂. It also modifies image slightly because it's based on diffusion algorithm so do not use it when you really want to preserve exact image colors and original image details.
And the result:
Last updated