Youchuan V8.2 Image to Image

Youchuan V8.2 Image to Image · Youchuan — Image to image · 9 aspect ratios. Call it through one queue API and pay for the options you pick.

modellane/youchuan-v8.2-image-to-image · Image to image · Youchuan

Image to image model: 9 aspect ratios.

Source image image — required The frame the generation starts from.
Prompt prompt — required, at most 1024 characters Describe what you want produced as concretely as you can.
Style reference sref — optional
Aspect ratio aspect_ratio — optional, options: 1:1, 9:16, 16:9, 4:3, 3:4, 2:3, 3:2, 9:21, 21:9 Sets whether the output is square, portrait, or landscape.
HD hd — optional, default: No When on, the output is produced in high resolution.
Stylize stylize — optional, default: 0, range: 0–1000 Sets how strongly the model's own style dominates the result.
Chaos chaos — optional, default: 0, range: 0–100 Increases the variety between results.
Weirdness weird — optional, default: 0, range: 0–3000 Pushes the result toward the unconventional.
Quality quality — optional, default: 1, options: 1, 4 Output quality; higher quality can take longer to generate.
Seed seed — optional, default: Random The same seed and the same settings produce a similar result; leave it empty and one is picked at random.

Output and retention

The generated file and your input are kept for seven days and then deleted.

Submit to the queue: POST /v1/queue/modellane/youchuan-v8.2-image-to-image

Status, result, cancellation and error codes work the same for every model; see the API docs.

Everything on this page is public; you need an account to run the model.