usamaehsan/klein-4b-lora-lab

Research only: train and test a LoRA on FLUX.2 klein 4B (Apache 2.0) edit pairs in one run.

Public
4 runs

Run usamaehsan/klein-4b-lora-lab with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
train_zip
string
Zip of training pairs (NNN_src.jpg, NNN_tgt.jpg, prompts.json)
test_zip
string
Zip of test inputs (NNN_src.jpg, prompts.json)
steps
integer
1200

Max: 4000

Training steps (0 = no training, base only)
rank
integer
32

Min: 4

Max: 128

None
lr
number
0.0001
None
train_width
integer
768
None
train_height
integer
576
None
test_width
integer
1024
None
test_height
integer
768
None
lora_scales
string
1.0,0.6
Comma list of LoRA scales for the test edits
seed
integer
42
None
train_on
string (enum)
base

Options:

base, distilled

None

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "string",
  "title": "Output",
  "format": "uri"
}