Base Model

1 Call Base Model

Click the GenAI button, then click the Base button, and then send prompts to generate the desired image. You can also send an image and use the caption as prompts to generate a new image. The Base model uses depth-to-image which allows you to pass a text prompt and an initial image to condition the generation of new images.

You can use the Base Model directly by sending the /gen_base command.

Call Base Model

2 Settings

Click the Settings button, then click the Base Settings button to enter the setting page of the Base Model. You can set parameters such as LoRA and LoRA Weight for the Base Model to get a more appropriate output.

Parameter Settings for the Base Model

2.1 LoRA

LoRA (Low-Rank Adaptation of Large Language Models) is a popular and lightweight training technique that significantly reduces the number of trainable parameters. Click the LoRA button and the bot will display the LoRA models that can be selected. You can also set a valid URL that can download the SD 1.5 LoRA model by sending message.

You can get the LoRA models from https://civitai.com/models. Note that the LoRA version must be SD 1.5. You can send multiple lora model urls, please use ^*^ to connect lora model urls.

Set Up LoRA Model

2.2 LoRA Weight

LoRA weight represents the influence weight of the LoRA model. After the LoRA setting is completed, the corresponding LoRA weight needs to be set.

When setting multiple LoRAs, the number of LoRA weights and the number of LoRAs must be equal.

Set Up LoRA Weight

2.3 Negative Prompt

Negative prompts tell GenAI model what you do not want in the output. Click the Negative Prompt button and send a message to customize negative prompts.

Custom Negative Prompts

2.4 CFG Scale

The CFG scale is a number from 0 to 10, indicating the influence of prompts on the generated images.

Set Up CFG Scale

2.5 Steps

The steps is a number from 0 to 50, indicating the number of denoising steps.

Set Up Steps

2.6 Seed

The seed is an integer greater than 0. With other parameters being the same, the same seed produces the same output. The default value for seed is 0, which means a random value is used.

Set Up Seed

3 Examples

3.1 Pre-provided LoRA Model

We provide multiple LoRA models for users to choose from. Here we take Cyberpunk_Anime_Style as an example to generate images.

Set Up Pre-provided LoRA

We send prompts to generate a cyberpunk style image.

Generate a Cyberpunk Style Image

3.2 Depth-to-Image

Let’s generate a mecha style image using the pre-provided Super_Robot LoRA. We set the LoRA Weight to 0.9.

Set Up Super_Robot LoRA
Generate a Mecha Image

We resend the generated mecha image and new prompts, to generate an Optimus Prime image.

Depth-to-Image Example
PreviousGet StartedNextSDXL Model

Last updated