Primary use stated or inferred cautiously from official documentation.
WeVisForensics-4B
A forensic system with five LoRA adapters on Qwen3.5-4B. An investigator coordinates appearance, physics, common-sense and visible-text inspectors alongside speech tools. The BF16 adapters were published on November 19.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | tencent/WeVisForensics |
|---|---|
| Model type | Multimodal · Video |
| Access model | Open weights |
| License | Apache 2.0 |
| Deployment | Self-hosted |
| Release | 19 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Video · Audio · Text |
| Exit | Text |
| Context window | Video-window inspection |
| maximum output | Verdict and explanation; does not generate video |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Hugging Face · Transformers |
Research into audiovisual forgery and explainable analysis of indicators.
These are adapters, not a standalone model: the base and additional tools with their licenses are required. False positives are possible; it does not prove authorship and must not make autonomous decisions about people. The single-GPU recipe specifies at least 24 GB.
What it can do
Orientation
Research into audiovisual forgery and explainable analysis of indicators.
Context
Video-window inspection · Verdict and explanation; does not generate video
Tools and integration
Not published
Access
Hugging Face · downloadable checkpoint
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | No published official API rate | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Self-hosted infrastructure cost | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
No verified official API tariff. Self-hosting requires memory, compute and maintenance; downloadable weights do not make inference free.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
The DTPO system reports 97.7% accuracy on GenBuster-Bench and 97.5% out-of-domain on GenBuster-Bench++. These concern the complete system with inspectors and tools, not an isolated adapter.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| GenBuster-Bench | 97.7 % | Accuracy | View source ↗ |
| GenBuster-Bench++ (out-of-domain) | 97.5 % | Accuracy | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
tencent/WeVisForensics
BF16 checkpoint.