Dual high-low noise LoRAs
According to the model card, the catalog provides high-noise and low-noise rank-64 adapters, one more creative and one more stable for image-to-video.
Open Source Model Profile · AakashTestCheck
Wan2.2-Distill-Loras
Wan2.2-Distill-Loras is an image-to-video LoRA collection from AakashTestCheck. Its model card documents rank-64 high-noise and low-noise adapters for Wan2.2-I2V-A14B with 4-step inference.
- Publisher
- AakashTestCheck
- Task
- image-to-video
- Model type
- Unknown
- License
- apache-2.0
- Library
- diffusers
- Publication status
- Accepted · not indexed
Model overview
Wan2.2-Distill-Loras is published by AakashTestCheck as an image-to-video LoRA collection. Hub tags list diffusers, distillation, and lora with Wan-AI/Wan2.2-I2V-A14B as base model and adapter, and card data records apache-2.0. According to the model card, the rank-64 high-noise and low-noise adapters enable 4-step inference with the Wan2.2 I2V base.
Recorded capabilities
4-step distilled inference
According to the model card, the LoRAs inherit distilled-model acceleration for high-quality video in four steps.
LightX2V and ComfyUI paths
According to the model card, users can pre-merge LoRA offline, load it online during inference, combine it with quantization, or use ComfyUI workflows.
Apache-2.0 diffusers record
Card data records apache-2.0, and the record is listed under the diffusers library with image-to-video and lora tags.
Use cases in the source record
- Four-step image-to-video generation that pairs the documented high-noise or low-noise LoRA with the required Wan2.2-I2V-A14B base.
- LightX2V offline-merge, online-loading, quantized, and ComfyUI deployments using the publisher-documented conversion and config paths.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No parameter count was extracted for these LoRA weights.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Quality, speed, and compatibility claims come from the publisher model card and were not independently verified by Ethen.
Source and provenance
Source: AakashTestCheck/Wan2.2-Distill-Loras
Captured: Unknown. Processed: 2026-09-07T19:36:04.453450+00:00.
🎬 Wan2.2 Distilled LoRA Models ⚡ High-Performance Video Generation with 4-Step Inference Using LoRA LoRA weights extracted from Wan2.2 distilled models - Flexible deployment with excellent generation quality 🌟 What's Special? ⚡ Flexible Deployment Base Model + LoRA : Can be combined with base models Offline Merging : Pre-merge LoRA into models Online Loading : Dynamically load LoRA during inference Multiple Frameworks : Supports LightX2V and ComfyUI 🎯 Dual Noise Control High Noise : More creative, diverse outputs Low Noise : More faithful to input, stable outputs Rank 64 LoRA, compact size 💾 Storage Efficient Small LoRA Size : S…
F001F002F003F004F005F006F007F008F009F010F011F016F019