Prompt
Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. For optimal performance of the model, it is recommended to use “360 view in the TOK style” at the end of the prompt.
Image
Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
Mask
Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
Aspect Ratio
Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
Height
256
1440
Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
Width
256
1440
Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
Prompt strength
0
1
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
Model
Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
Num outputs
1
4
Number of outputs to generate
Num inference steps
1
50
Number of denoising steps. More steps can give more detailed images, but take longer.
Guidance scale
0
10
Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
Seed
Random seed. Set for reproducible generation
Output Format
Format of the output images
Output quality
0
100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Disable safety checker
Disable safety checker for generated images.
Go fast
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
Megapixels
Approximate number of megapixels for generated image
Lora scale
-1
3
Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
Extra lora
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
Extra lora scale
-1
3
Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.