OppaiOracle experimental-X1.1
OppaiOracle experimental-X1.1 is an experimental multi-label tagger for anime and illustration images, released as FP32 ONNX and safetensors weights. It uses 448×448 inputs and returns tag names with sigmoid scores; the release includes inference scripts and a 14,994-tag vocabulary.
What it does
Use it to generate tag-name suggestions and scores for anime or illustration images, then review them before applying them to a dataset.
- Availability
- Public download from Hugging Face; FP32 ONNX and FP32 safetensors formats
- Pricing model
- Not established
- Deployment
- Local inference; no network requests during inference
- Privacy
- Local inference does not make network requests
- Licence
- Educational Use Only License; commercial use prohibited
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The model is a multi-label anime and illustration tagger. [1]
It is a multi-label anime and illustration tagger, released in **FP32 ONNX and
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The release provides FP32 ONNX and FP32 safetensors weights. [1]
- The supplied inference paths support local CPU inference, and CUDA is available with a corresponding environment. [1]
- Local inference does not make network requests. [1]
inference does not make network requests.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The Educational Use Only License permits the educational uses described in the license and prohibits commercial use. [1]
the educational uses described in that file and prohibits commercial use.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The release is experimental, and the source cautions that tag reliability varies and the model is not validated as a safety classifier. [1]
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/Grio43/OppaiOracle-experimental-X1.1
Retrieved 2026-10-27 01:17 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-14 20:18 UTC | material change | capability, deployment, pricing, availability, privacy | Current |
| 1 | 2026-10-12 22:08 UTC | publication | None | Current |
In briefs
1- Muse Wonder is aimed at document work, workflows, and coding Daily brief 2026-10-12
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.