mlboydaisuke / LaMa-Dilated-LiteRT

huggingface.co
Total runs: 42
24-hour runs: -4
7-day runs: 19
30-day runs: 2
Model's Last Updated: August 15 2026
image-to-image

Introduction of LaMa-Dilated-LiteRT

Model Details of LaMa-Dilated-LiteRT

LaMa-Dilated — LiteRT (TFLite) GPU

On-device LiteRT ( .tflite ) build of LaMa-Dilated large-mask image inpainting: paint a mask over an unwanted object and the model fills the region naturally.

This is the LaMa-Dilated variant (FFT blocks replaced with dilated convolutions for GPU friendliness), obtained from Qualcomm AI Hub . It is a pure CNN — all 361 ops are LiteRT GPU-native (no Flex ops, no CPU fallback on Qualcomm GPUs).

Files
File Size Description
lama_dilated.tflite 174 MB FP32 single-graph model
I/O
  • Inputs (NHWC, both [0, 1] ):
    • image [1, 512, 512, 3] — RGB
    • mask [1, 512, 512, 1] — single channel, 1 = region to inpaint , 0 = keep
  • Output :
    • painted_image [1, 512, 512, 3] — inpainted RGB

The model preserves the unmasked region exactly and only synthesizes inside the mask.

Usage (Android, LiteRT CompiledModel)
val model = CompiledModel.create(
    context.assets, "lama_dilated.tflite",
    CompiledModel.Options(Accelerator.GPU), null
)
val inputs = model.createInputBuffers()
val outputs = model.createOutputBuffers()
inputs[0].writeFloat(imageFloats)   // [1,512,512,3] RGB [0,1]
inputs[1].writeFloat(maskFloats)    // [1,512,512,1]  1=hole
model.run(inputs, outputs)
val painted = outputs[0].readFloat() // [1,512,512,3]
On-device note

The graph contains 3 TRANSPOSE_CONV ops. These run on Qualcomm Adreno GPUs (the hardware Qualcomm AI Hub optimized for). Some other GPU delegates may not accept TRANSPOSE_CONV ; verify on your target device.

License & attribution
  • License: Apache-2.0 .
  • Original model: advimman/lama (LaMa, © 2021 Samsung Research), Apache-2.0.
  • Converted/optimized .tflite from Qualcomm AI Hub — lama_dilated .
  • This repository only re-hosts the LiteRT .tflite for convenient on-device use; all credit to the original authors and Qualcomm AI Hub.

Runs of mlboydaisuke LaMa-Dilated-LiteRT on huggingface.co

42
Total runs
-4
24-hour runs
0
3-day runs
19
7-day runs
2
30-day runs

More Information About LaMa-Dilated-LiteRT huggingface.co Model

More LaMa-Dilated-LiteRT license Visit here:

https://choosealicense.com/licenses/apache-2.0

LaMa-Dilated-LiteRT huggingface.co

LaMa-Dilated-LiteRT huggingface.co is an AI model on huggingface.co that provides LaMa-Dilated-LiteRT's model effect (), which can be used instantly with this mlboydaisuke LaMa-Dilated-LiteRT model. huggingface.co supports a free trial of the LaMa-Dilated-LiteRT model, and also provides paid use of the LaMa-Dilated-LiteRT. Support call LaMa-Dilated-LiteRT model through api, including Node.js, Python, http.

LaMa-Dilated-LiteRT huggingface.co Url

https://huggingface.co/mlboydaisuke/LaMa-Dilated-LiteRT

mlboydaisuke LaMa-Dilated-LiteRT online free

LaMa-Dilated-LiteRT huggingface.co is an online trial and call api platform, which integrates LaMa-Dilated-LiteRT's modeling effects, including api services, and provides a free online trial of LaMa-Dilated-LiteRT, you can try LaMa-Dilated-LiteRT online for free by clicking the link below.

mlboydaisuke LaMa-Dilated-LiteRT online free url in huggingface.co:

https://huggingface.co/mlboydaisuke/LaMa-Dilated-LiteRT

LaMa-Dilated-LiteRT install

LaMa-Dilated-LiteRT is an open source model from GitHub that offers a free installation service, and any user can find LaMa-Dilated-LiteRT on GitHub to install. At the same time, huggingface.co provides the effect of LaMa-Dilated-LiteRT install, users can directly use LaMa-Dilated-LiteRT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

LaMa-Dilated-LiteRT install url in huggingface.co:

https://huggingface.co/mlboydaisuke/LaMa-Dilated-LiteRT

Url of LaMa-Dilated-LiteRT

LaMa-Dilated-LiteRT huggingface.co Url

Provider of LaMa-Dilated-LiteRT huggingface.co

mlboydaisuke
ORGANIZATIONS

Other API from mlboydaisuke