Image
Fooocus
Generate styled images, edit a masked region or upscale and vary an existing image with Fooocus.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Fooocus. Review your own result before publishing.
A starting point.
Try a visual treatment from a prompt, or start with an image when you need a local edit or a larger version. Choose the operation that matches the change you want.
Before you publish.
Inspect lettering, edges and fine detail. For inpainting, compare the masked boundary with the original; for upscaling, check that new details remain plausible.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Inputs and settings
Choose generation, inpainting or upscale/variation. Inpainting needs inpaint_image_url; upscale/variation needs uov_image_url. Use a mask for a specific region when the selected operation exposes it.
Choose styles, performance and num_images within the current form. Record the seed when comparing changes, and choose output_format for delivery.
The quote reserves a maximum of 300 compute seconds per run. The provider-recorded runtime determines the final charge; unused reserved credits return to your balance. This ceiling does not guarantee a completion time.
Supported inputs
These fields come from the current studio form for fooocus. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
aspect_ratio | Text | Optional | — |
control_image_stop_at | Number | Optional | ≥ 0 · ≤ 1 |
control_image_url | Text | Optional | — |
control_image_weight | Number | Optional | ≥ 0 · ≤ 2 |
control_type | Text | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 30 |
inpaint_image_url | Text | Optional | — |
loras | List | Optional | — |
mask_image_url | Text | Optional | — |
mixing_image_prompt_and_inpaint | On/off | Optional | — |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
output_format | Text | Optional | png, jpeg, webp |
performance | Text | Optional | — |
prompt | Text | Optional | — |
refiner_model | Text | Optional | — |
refiner_switch | Number | Optional | ≥ 0 · ≤ 1 |
seed | Whole number | Optional | — |
sharpness | Number | Optional | ≥ 0 · ≤ 30 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
text-to-image (inpaint)fooocus/inpaint
Supported inputs
These fields come from the current studio form for fooocus/inpaint. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
inpaint_image_url | Text | Required | — |
aspect_ratio | Text | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 30 |
image_prompt_1 | Object | Optional | — |
image_prompt_2 | Object | Optional | — |
image_prompt_3 | Object | Optional | — |
image_prompt_4 | Object | Optional | — |
inpaint_additional_prompt | Text | Optional | — |
inpaint_disable_initial_latent | On/off | Optional | — |
inpaint_engine | Text | Optional | — |
inpaint_erode_or_dilate | Number | Optional | ≥ -64 · ≤ 64 |
inpaint_mode | Text | Optional | — |
inpaint_respective_field | Number | Optional | ≥ 0 · ≤ 1 |
inpaint_strength | Number | Optional | ≤ 1 · > 0 |
invert_mask | On/off | Optional | — |
loras | List | Optional | — |
mask_image_url | Text | Optional | — |
mixing_image_prompt_and_inpaint | On/off | Optional | — |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
outpaint_selections | List | Optional | — |
output_format | Text | Optional | png, jpeg, webp |
override_inpaint_options | On/off | Optional | — |
performance | Text | Optional | — |
prompt | Text | Optional | — |
refiner_model | Text | Optional | — |
refiner_switch | Number | Optional | ≥ 0 · ≤ 1 |
seed | Whole number | Optional | — |
sharpness | Number | Optional | ≥ 0 · ≤ 30 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
text-to-image (upscale-or-vary)fooocus/upscale-or-vary
Supported inputs
These fields come from the current studio form for fooocus/upscale-or-vary. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
uov_image_url | Text | Required | — |
aspect_ratio | Text | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 30 |
image_prompt_1 | Object | Optional | — |
image_prompt_2 | Object | Optional | — |
image_prompt_3 | Object | Optional | — |
image_prompt_4 | Object | Optional | — |
loras | List | Optional | — |
mixing_image_prompt_and_vary_upscale | On/off | Optional | — |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
output_format | Text | Optional | png, jpeg, webp |
performance | Text | Optional | — |
prompt | Text | Optional | — |
refiner_model | Text | Optional | — |
refiner_switch | Number | Optional | ≥ 0 · ≤ 1 |
seed | Whole number | Optional | — |
sharpness | Number | Optional | ≥ 0 · ≤ 30 |
uov_method | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Fooocus through the API.
Start with this model ID for the endpoint featured on this page:
fooocus
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-image ·
fooocus - text-to-image (inpaint) ·
fooocus/inpaint - text-to-image (upscale-or-vary) ·
fooocus/upscale-or-vary
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.