Kim2091/ClearRealityV1
By Kim2091 · ↓ 0 · ♥ 27 · Updated 2026-02-11
What's in this repo
This page lists the files in Kim2091/ClearRealityV1, including 4x-ClearRealityV1_Soft-fp16-opset14.onnx, 4x-ClearRealityV1_Soft-fp16-opset15.onnx, 4x-ClearRealityV1_Soft-fp16-opset16.onnx and more.
- 16 ONNX models (.onnx files)
- 30 files, including 16 .onnx, 4 .bin, 4 .param, 2 .pth, 2 .safetensors, 1 .md
- Last updated 2026-02-11
ONNX files
| File | Size | Download |
|---|---|---|
| ONNX/Soft_fp16/4x-ClearRealityV1_Soft-fp16-opset14.onnx | — | Download |
| ONNX/Soft_fp16/4x-ClearRealityV1_Soft-fp16-opset15.onnx | — | Download |
| ONNX/Soft_fp16/4x-ClearRealityV1_Soft-fp16-opset16.onnx | — | Download |
| ONNX/Soft_fp16/4x-ClearRealityV1_Soft-fp16-opset17.onnx | — | Download |
| ONNX/Soft_fp32/4x-ClearRealityV1_Soft-fp32-opset14.onnx | — | Download |
| ONNX/Soft_fp32/4x-ClearRealityV1_Soft-fp32-opset15.onnx | — | Download |
| ONNX/Soft_fp32/4x-ClearRealityV1_Soft-fp32-opset16.onnx | — | Download |
| ONNX/Soft_fp32/4x-ClearRealityV1_Soft-fp32-opset17.onnx | — | Download |
| ONNX/fp16/4x-ClearRealityV1-fp16-opset14.onnx | — | Download |
| ONNX/fp16/4x-ClearRealityV1-fp16-opset15.onnx | — | Download |
Showing 10 of 16 .onnx files — see the full file list on the right.
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Name: ClearRealityV1 Soft + Normal
License: Apache 2.0
Link: https://mega.nz/folder/Xc4wnC7T#yUS5-9-AbRxLhpdPW_8f2w
Model Architecture: SPAN
Scale: 4
Purpose: Realistic images of humans, foliage, trees, buildings, etc.
Iterations: 300k (over multiple models)
batch_size: 12-20
HR_size: 128-256
Epoch: 40?
Dataset: My own UltraSharpV2 dataset, my 8k dataset (v2), Nomos8k, and FaceUp
Dataset_size: 19k tiles
OTF Training No (made with datasetDestroyer)
Pretrained_Model_G: Official pretrain
Description: Nice to release a model again! This one is intended for realistic imagery, and works especially well on faces, hair, and nature shots. I trained this model on SPAN, which as of the time of release, you'll need chaiNNer-nightly for. I aimed for a softer, more natural look for this model with as few artifacts as possible.
In addition to the Normal model, I've included a "soft" model. The Soft model is... softer. Basically it was an earlier version of the model with a more limited dataset. It produces more natural output on games or rendered content, but suffers a bit more with realistic stuff.
Note: In shots with DOF (depth of field) or bokeh, unfortunately there will be artifacts. Sorry
Model info
Created: 2024-01-03
Updated: 2026-02-11
View on Hugging Face