GingerLabsPlatform/GingerLabs-Wan2.2-T2V-A14B
text-to-video model by GingerLabsPlatform
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 GingerLabs-tuned derivative of Wan-AI/Wan2.2-T2V-A14B, packaged as quantized HighNoise and LowNoise diffusion-model pairs for ComfyUI. This is a quantized-weights-only release. It does not include the VAE, text encoder, or other pipeline assets required for generation. Download GingerLabsT2VWorkflow.json The reference workflow uses ComfyUI-WanVideoWrapper for both GGUF and scaled FP8. It defaults to the balanced Q5KM pair, portable sdpa attention, a 720 × 1280 portrait canvas, 33 frames, and 16 fps. No acceleration LoRA is required. The reference workflow supports only nsfwwanumt5-xxlbf16.safetensors from NSFW-API/NSFW-Wan-UMT5-XXL. Other UMT5-XXL checkpoints are not supported or validated. Do not select the sibling nsfwwanumt5-xxlfp8scaled.safetensors file with this workflow. WanVideoWrapper 1.3.6's LoadWanVideoT5TextEncoder node does not support scaled-FP8 T5 weights. Start with these values: The HighNoise and LowNoise models split one schedule. With 8 total steps, HighNoise runs steps 0–4, then LowNoise continues from 4–end. This is 8 total denoising steps (4 + 4), not 8 steps per model. Both…
Read the full model card ↗ · Preview checked 2026-11-05T07:03:23.608Z
Inside the original model card — Document outline
- GingerLabs Wan 2.2 T2V A14B
- Reference ComfyUI workflow
- Required files and nodes
- Required text encoder
- GingerLabs sampling recipe
- Download a matching pair
- Loader settings
- Repository layout
- Download example
- Resolution, duration, and memory tips
- Quantization details
- Validation
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. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
GingerLabsPlatform/GingerLabs-Wan2.2-T2V-A14B is a text-to-video model repository published by GingerLabsPlatform on Hugging Face. The source reports the wan2.2 library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- wan2.2
- Recent downloads (30 days)
- 6,307
- Cumulative likes
- 5
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-08-01T04:41:17.000Z
- Last modified
- 2026-08-02T18:55:18.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Wan-AI/Wan2.2-T2V-A14B
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 2026-11-05T06:54:25.261Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-T2V-A14B-GGUF
QuantStack/Wan2.2-TI2V-5B-GGUF