H4RUming/Velyn-GMNet-Camera-v1
image-to-image model by H4RUming
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A camera-adapted version of GMNet, trained to predict a scalar gain map for expanding an SDR photo into HDR. This is the model bundled in Velyn v1.2. Velyn fine-tuned the published GMNet real-world weights. The architecture and 1,921,827 parameters are unchanged. Output is positive scalar log2 gain in 0…log2(5) EV, equivalent to 1…5× linear brightness. This model does not predict dimming, recover clipped detail, or reconstruct known scene luminance. The Core ML packages are identical to those in Velyn v1.2. Their global branch uses FP32 and local operators use FP16. Equivalent fixed pooling and static kernel operators improve accelerator compatibility. Deployment target is iOS 18 or later for these model packages; Velyn itself requires iOS 27 because of other app APIs. Download this repository, then run: gain.npy is a float32 [height, width] array in EV, not a finished HDR photo. The example reads an SDR raster, applies EXIF orientation, and…
Read the full model card ↗ · Preview checked 2026-10-02T07:54:30.186Z
Inside the original model card — Document outline
- Velyn GMNet Camera v1
- Files
- Use locally
- Training and provenance
- Evaluation
- Intended use and limits
- License and credit
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
H4RUming/Velyn-GMNet-Camera-v1 is a image-to-image model repository published by H4RUming on Hugging Face. The source reports the pytorch library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-to-image
- Library
- pytorch
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 1,921,827
- Architecture
- Not reported
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-10-02T06:14:55.000Z
- Last modified
- 2026-10-02T06:15:01.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-02T06:39:29.113Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
black-forest-labs/FLUX.1-Kontext-dev
black-forest-labs/FLUX.2-klein-9B