# face-parsing by Jonathan Dinu: Open-Weight Model Source: https://savrn.com/models/face-parsing Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve face-parsing (85M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [face-parsing on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/face-parsing/gpus) ## SAVRN's Notes on face-parsing Face parsing labels every pixel of a face image: skin, eyes, brows, lips, hair and more. This model is a SegFormer fine-tuned on CelebAMask-HQ, 85M parameters, and is used for virtual try-on, photo editing and creative tools. The repository states no license, so treat it as research use until the author publishes terms. It learned from celebrity photos, which skew toward certain lighting, poses and demographics; test it across the range of faces your users actually have before building a product on it. SAVRN Research, 2026-09-18 ## Model Card Semantic segmentation model fine-tuned from nvidia/mit-b5 with CelebAMask-HQ for face parsing. For additional options, see the Transformers Segformer docs. Exhaustive list of labels can be extracted from config.json. Since p5.js uses an animation loop abstraction, we need to take care loading the model and making predictions. While the capabilities of computer vision models are impressive, they can also reinforce or exacerbate social biases. The CelebAMask-HQ dataset used for fine-tuning is large but not necessarily perfectly diverse or representative. Also, they are images of.... just celebrities. Excerpt from the card by Jonathan Dinu. ## Configuration Architecture SegformerForSemanticSegmentation Model type segformer ## Identity and Version Repository jonathandinu/face-parsing Publisher Jonathan Dinu Task Image segmentation Modality Image Library transformers Parameters 85M parameters Languages en Revision 758b82e15a0178c9db39c1ff666a8b56e3a550c8 First published 2022-07-06 Last updated 2026-02-18 ## Files and Weights 10 files, 1.1 GB in total. The weights are 4 files totalling 1.1 GB in bin, onnx, safetensors. Weights4 files · 1.1 GB Configuration3 files · 2.8 KB Documentation1 file · 5.6 KB Other1 file · 645.1 KB Repository1 file · 1.2 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 338.6 MB | c2bec795a8c2 | | onnx/model.onnx | Weights | 340.3 MB | 6d4e67af60ff | | onnx/model_quantized.onnx | Weights | 89.4 MB | 5bab9bfb3cb9 | | pytorch_model.bin | Weights | 338.8 MB | e0139f52e953 | | config.json | Configuration | 1.7 KB | — | | preprocessor_config.json | Configuration | 374 B | — | | quantize_config.json | Configuration | 749 B | — | | README.md | Documentation | 5.6 KB | — | | demo.png | Other | 645.1 KB | — | | .gitattributes | Repository | 1.2 KB | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 1.1 GB [Download from Jonathan Dinu](https://huggingface.co/jonathandinu/face-parsing) Released by Jonathan Dinu through its official repository on Hugging Face. ## Built From - Described by [arXiv:2105.15203](https://savrn.com/papers/segformer-simple-and-efficient-design-for-semantic-segmentation-with-transformers) - Trained on (disclosed) celebamaskhq ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.1 GB | | 16-bit | 0.2 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About face-parsing ### How much GPU memory does face-parsing need? About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (85M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run face-parsing on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ## Similar Models Model · Image segmentation ### [dinov3-pointing-pilot-v1](https://savrn.com/models/dinov3-pointing-pilot-v1) [Fire Viewer](https://savrn.com/model-publishers/fireviewer) Research archive, currently publicly visible on the Hub, of a five-epoch DINOv3 ViT-B/16 multi-task pilot for visible fire/smoke presence, segmentation, point localization and explicit visual abstention. This repository preserves a completed, reloadable experiment. It is not a production model and not independently benchmarked. The retained release records describe a private pilot policy; current public visibility does not resolve that restriction or establish redistribution permission. The word “pilot” is part of the model identity and should not be removed in downstream documentation. The metrics below come from the campaign validation split. They are not an independent benchmark and must… Open weights other 94M parameters pytorch [View model](https://savrn.com/models/dinov3-pointing-pilot-v1) Model · Image segmentation ### [BEN2](https://savrn.com/models/ben2) [BackgroundErase](https://savrn.com/model-publishers/pramallc) BEN2 (Background Erase Network) introduces a novel approach to foreground segmentation through its innovative Confidence Guided Matting (CGM) pipeline. The architecture employs a refiner network that targets and processes pixels where the base model exhibits lower confidence levels, resulting in more precise and reliable matting results. This model is built on BEN: BEN2 was trained on the DIS5k and our 22K proprietary segmentation dataset. Our enhanced model delivers superior performance in hair matting, 4K processing, object segmentation, and edge refinement. Our Base model is open source. To try the full model through our free web demo or integrate BEN2 into your project with our API… Open weights mit 95M parameters ben2 [View model](https://savrn.com/models/ben2) Model · Image segmentation ### [mask2former-swin-small-ade-semantic](https://savrn.com/models/mask2former-swin-small-ade-semantic) [AI at Meta](https://savrn.com/model-publishers/facebook) Mask2Former model trained on ADE20k semantic segmentation (small-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Open weights other 69M parameters transformers [View model](https://savrn.com/models/mask2former-swin-small-ade-semantic) Model · Image segmentation ### [mask2former-swin-small-coco-instance](https://savrn.com/models/mask2former-swin-small-coco-instance) [AI at Meta](https://savrn.com/model-publishers/facebook) Mask2Former model trained on COCO instance segmentation (small-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Open weights other 69M parameters transformers [View model](https://savrn.com/models/mask2former-swin-small-coco-instance) Model · Image segmentation ### [fashn-human-parser](https://savrn.com/models/fashn-human-parser) [FASHN](https://savrn.com/model-publishers/fashn-ai) A SegFormer-B4 model fine-tuned for human parsing with 18 semantic classes, optimized for fashion and virtual try-on applications. This model segments human images into 18 semantic categories including body parts (face, hair, arms, hands, legs, feet, torso), clothing items (top, dress, skirt, pants, belt, scarf), and accessories (bag, hat, glasses, jewelry). The pipeline automatically manages GPU/CPU and returns per-class masks at the original image resolution. For maximum accuracy, use our Python package which implements the exact preprocessing used during training: The package uses cv2.INTERAREA for resizing (matching training), while the HuggingFace pipeline uses PIL LANCZOS. Labels… Open weights other 64M parameters transformers [View model](https://savrn.com/models/fashn-human-parser) Model · Image segmentation ### [mask2former-swin-base-coco-panoptic](https://savrn.com/models/mask2former-swin-base-coco-panoptic) [AI at Meta](https://savrn.com/model-publishers/facebook) Mask2Former model trained on COCO panoptic segmentation (base-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Open weights other 107M parameters transformers [View model](https://savrn.com/models/mask2former-swin-base-coco-panoptic) ## Jonathan Dinu [All models and datasets](https://savrn.com/model-publishers/jonathandinu) ## Versions - [758b82e15a01](https://savrn.com/models/face-parsing/versions/758b82e15a01) · current 2026-09-18 ## Explore More - [All image segmentation models](https://savrn.com/models/tasks/image-segmentation) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/jonathandinu/face-parsing) - [How the hub is built](https://savrn.com/model-hub/methodology)