cinemasetfree.com
ludocomito/flux-caravaggio
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
prompt * | string | 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. | — | — |
aspect_ratio | string | Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode | "1:1" | 1:1 16:9 21:9 3:2 2:3 4:5 5:4 3:4 4:3 9:16 9:21 custom |
disable_safety_checker | boolean | Disable safety checker for generated images. | false | — |
extra_lora | string | 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 | number | 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. | 1 | min: -1, max: 3 |
go_fast | boolean | Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 | false | — |
guidance_scale | number | 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 | 3 | min: 0, max: 10 |
height | integer | 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 | — | min: 256, max: 1440 |
image | string (uri) | Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. | — | — |
lora_scale | number | 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. | 1 | min: -1, max: 3 |
mask | string (uri) | Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. | — | — |
megapixels | string | Approximate number of megapixels for generated image | "1" | 1 0.25 |
model | string | Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. | "dev" | dev schnell |
num_inference_steps | integer | Number of denoising steps. More steps can give more detailed images, but take longer. | 28 | min: 1, max: 50 |
num_outputs | integer | Number of outputs to generate | 1 | min: 1, max: 4 |
output_format | string | Format of the output images | "webp" | webp jpg png |
output_quality | integer | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs | 80 | min: 0, max: 100 |
prompt_strength | number | Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image | 0.8 | min: 0, max: 1 |
replicate_weights | string | 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' | — | — |
seed | integer | Random seed. Set for reproducible generation | — | — |
width | integer | 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 | — | min: 256, max: 1440 |
prompt required string 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.
aspect_ratio string Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
"1:1" disable_safety_checker boolean Disable safety checker for generated images.
false extra_lora string 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 number 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.
1 min: -1, max: 3 go_fast boolean Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
false guidance_scale number 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
3 min: 0, max: 10 height integer 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
image string Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
lora_scale number 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.
1 min: -1, max: 3 mask string Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
megapixels string Approximate number of megapixels for generated image
"1" model string Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
"dev" num_inference_steps integer Number of denoising steps. More steps can give more detailed images, but take longer.
28 min: 1, max: 50 num_outputs integer Number of outputs to generate
1 min: 1, max: 4 output_format string Format of the output images
"webp" output_quality integer Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
80 min: 0, max: 100 prompt_strength number Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
0.8 min: 0, max: 1 replicate_weights string 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'
seed integer Random seed. Set for reproducible generation
width integer 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
383a996094f5 Updated: 2/26/2026 166 runs