You're looking at a specific version of this model. Jump to the model overview.

laion-ai /laionide:26a8ba9d

Input

string
Shift + Return to add a new line

Text prompt to use. Keep it simple/literal and avoid using poetic language (unlike CLIP).

Default: ""

integer
(minimum: 1, maximum: 6)

Batch size. Number of generations to predict

Default: 3

integer

Must be multiple of 8. Going above 64 is not recommended. Actual image will be 4x larger.

integer

Must be multiple of 8. Going above 64 is not recommended. Actual image size will be 4x larger.

boolean

If true, uses both the base and upsample models. If false, only the (finetuned) base model is used. This is useful for testing the upsampler, which is not finetuned.

Default: false

number

Classifier-free guidance scale. Higher values move further away from unconditional outputs. Lower values move closer to unconditional outputs. Negative values guide towards semantically opposite classes. 4-16 is a reasonable range.

Default: 4

number

Upsample temperature. Consider lowering to ~0.997 for blurry images with fewer artifacts.

string

Number of timesteps to use for base model. Going above 150 has diminishing returns.

Default: "100"

integer

Seed for reproducibility

Default: 0

boolean

If true, uses the noisy CLIP model. Only works with image size = (64, 64). This CLIP is not finetuned and so may not very well.

Default: false

Output

No output yet! Press "Submit" to start a prediction.