# \#onnx **URL:** https://forum.logik.tv/tag/onnx/917.md [Latest](https://forum.logik.tv/latest.md) · [Categories](https://forum.logik.tv/categories.md) · [Tags](https://forum.logik.tv/tags.md) --- ## [ONNX models (Inference)](https://forum.logik.tv/t/onnx-models-inference/11148)
**Author:** [@bryanb](https://forum.logik.tv/u/bryanb)\ **Replies:** 8\ **Last updated:** [May 12, 2026, 11:45am UTC](https://forum.logik.tv/t/onnx-models-inference/11148 "2026-05-12T11:45:04Z")
Anyone that has tried the new inference node (flame 2024.1): – any ONNX models to recommend? – where do you go to check out available models? This is all new to me. --- ## [Updated BiRefNet models for 2026.2](https://forum.logik.tv/t/updated-birefnet-models-for-2026-2/13727)
**Author:** [@allklier](https://forum.logik.tv/u/allklier)\ **Replies:** 3\ **Last updated:** [March 5, 2026, 7:37pm UTC](https://forum.logik.tv/t/updated-birefnet-models-for-2026-2/13727 "2026-03-05T19:37:50Z")
With the release of 2026.2 the way BiRefNet works has changed slightly. The extra matchbox nodes are no longer needed for pre/post processing, and those parameters have migrated into the json file packaged with the .inf … --- ## [Inference JSON parameters](https://forum.logik.tv/t/inference-json-parameters/13886)
**Author:** [@allklier](https://forum.logik.tv/u/allklier)\ **Replies:** 9\ **Last updated:** [December 17, 2025, 12:14pm UTC](https://forum.logik.tv/t/inference-json-parameters/13886 "2025-12-17T12:14:18Z")
When making the inference files for DA3 yesterday, I couldn’t figure out how to instruct the node to do the resizing internally. The model expects 1022x1022 inputs. But the .json file doesn’t seem to have any parameter … --- ## [Inference - export to onnx problem](https://forum.logik.tv/t/inference-export-to-onnx-problem/13052)
**Author:** [@Stefan](https://forum.logik.tv/u/Stefan)\ **Replies:** 2\ **Last updated:** [July 9, 2025, 5:56pm UTC](https://forum.logik.tv/t/inference-export-to-onnx-problem/13052 "2025-07-09T17:56:49Z")
I’m trying to export DepthAnything v2 to onnx, since I know it’s possible, and just want to learn how it works. I can get something that works at 518x518, but whatever I try to allow for various resolutions fails. I ca… --- ## [Inference node / downloading ONNX models](https://forum.logik.tv/t/inference-node-downloading-onnx-models/12615)
**Author:** [@David.Marin](https://forum.logik.tv/u/David.Marin)\ **Replies:** 1\ **Last updated:** [April 7, 2025, 2:19pm UTC](https://forum.logik.tv/t/inference-node-downloading-onnx-models/12615 "2025-04-07T14:19:21Z")
Hey there! I’m downloading onnx models from this website, but It’s not being really successful. I know from other posts about the multichannel problem, but none of the models that I downloaded worked. I tried the infe… --- ## [Magic mask in inference ONNX](https://forum.logik.tv/t/magic-mask-in-inference-onnx/11345)
**Author:** [@Jonhollis](https://forum.logik.tv/u/Jonhollis)\ **Replies:** 12\ **Last updated:** [September 13, 2024, 12:11pm UTC](https://forum.logik.tv/t/magic-mask-in-inference-onnx/11345 "2024-09-13T12:11:35Z")
hey all. anyone seen a ONNX type of thing out there that will do what resolves magic mask will do? I have no idea where to look for ONNX software --- ## [ONNX Models & Logik Users](https://forum.logik.tv/t/onnx-models-logik-users/11245)
**Author:** [@allklier](https://forum.logik.tv/u/allklier)\ **Replies:** 9\ **Last updated:** [September 4, 2024, 9:57pm UTC](https://forum.logik.tv/t/onnx-models-logik-users/11245 "2024-09-04T21:57:42Z")
As we’re looking to make more ONNX models available to the group, we should discuss the legal caveats we should observe. There’s a good reason why it took a while for ADSK to come out with new ML tools. The latest think… --- ## [Additional ONNX Models](https://forum.logik.tv/t/additional-onnx-models/11242)
**Author:** [@allklier](https://forum.logik.tv/u/allklier)\ **Replies:** 3\ **Last updated:** [August 18, 2024, 9:29pm UTC](https://forum.logik.tv/t/additional-onnx-models/11242 "2024-08-18T21:29:21Z")
Disclaimer: This post contains a link to a 3rd party ML model. This post and its poster do not make any warranties in regards to the model’s legal status and use. Anyone accessing and downloading this link must independ…