Qwen Image Edit 2511 Lightning
Qwen-Image-Edit-2511-Lightning is a collection of optimized models tailored for image editing tasks, leveraging step distillation and quantization techniques to deliver high-efficiency inference performance. This...
Fuente del modelo
- Tipo
- Other
- Tamaño del archivo
- 155 MB–19,2 GB
- Modelo base
- Qwen/Qwen-Image-Edit-2511
- Versión
- vRevision d74eba1
- Actualizado
- 5 oct 2026
- Publicador
- @lightx2v
- Descargas
- 348,8 mil
- Tareas
- Edición de imagen, Imagen a imagen, Texto a imagen
- Fuente
- Hugging Face
Descripción de la fuente
Qwen-Image-Edit-2511-Lightning
Model Overview
Qwen-Image-Edit-2511-Lightning is a collection of optimized models tailored for image editing tasks, leveraging step distillation and quantization techniques to deliver high-efficiency inference performance. This repository hosts three core model files with distinct characteristics:
| Model File Name | Type | Key Features |
|---|---|---|
Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors | 4-step Distilled LoRA | BF16 precision, lightweight, 4-step inference |
Qwen-Image-Edit-2511-Lightning-4steps-V1.0-fp32.safetensors | 4-step Distilled LoRA | FP32 precision, high accuracy, 4-step inference |
qwen_image_edit_2511_fp8_e4m3fn_scaled_lightning.safetensors | FP8 Quantized | FP8 (e4m3fn scaled) precision, fused with 4-step distilled LoRA, optimized for low-memory deployment |
Usage Instructions
This model suite supports two mainstream usage frameworks, with detailed guides provided below:
1. Qwen-Image-Lightning Framework
For full documentation on model usage within the Qwen-Image-Lightning ecosystem (including environment setup, inference pipelines, and customization), please refer to: Qwen-Image-Lightning GitHub Repository
2. LightX2V Framework
The models are fully compatible with the LightX2V lightweight video/image generation inference framework. For step-by-step usage examples, configuration templates, and performance optimization tips, see: LightX2V Qwen Image Edit Documentation
Key Optimizations
- Step Distillation: The LoRA models reduce the original inference steps to just 4 steps, achieving significant speedup (≈10x faster than standard 40-step inference) while preserving image editing quality.
- FP8 Quantization: The quantized base model balances performance and resource efficiency, reducing GPU memory usage by ~50% compared to FP32 while maintaining editing fidelity.
Support
For technical issues, feature requests, or integration questions:
- Open an issue in the Qwen-Image-Lightning repo (for Qwen framework-specific questions)
- Open an issue in the LightX2V repo (for LightX2V integration questions)
Recursos relacionados
3 conexiones
Recursos relacionados
3 conexionesFuentes
1 fuente
Fuentes
1 fuenteVerificado 5 oct
Artefactos del modelo
64 artefactos
Artefactos del modelo
64 artefactosqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_4steps_v1.0.safetensors
safetensors · 19,2 GB · SHA-256 56f82dcb4fc4…418d · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_8steps_v1.0.safetensors
safetensors · 19,1 GB · SHA-256 69702a1ea4d8…9b9d · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_comfyui_4steps_v1.0.safetensors
safetensors · 19,0 GB · SHA-256 16d03fd9bab3…c36f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_0.safetensors
safetensors · 325 MB · SHA-256 c5d1fc8745d4…cb99 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_1.safetensors
safetensors · 325 MB · SHA-256 d10fd484b089…8d0b · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_10.safetensors
safetensors · 325 MB · SHA-256 3cddabafd951…8944 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_11.safetensors
safetensors · 325 MB · SHA-256 0c47965672b7…d654 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_12.safetensors
safetensors · 325 MB · SHA-256 90e1b6849148…0bce · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_13.safetensors
safetensors · 325 MB · SHA-256 8cae34c9d635…ffb2 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_14.safetensors
safetensors · 325 MB · SHA-256 51680c2145b5…c200 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_15.safetensors
safetensors · 325 MB · SHA-256 78dfc1abd3bf…825d · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_16.safetensors
safetensors · 325 MB · SHA-256 0377fe07cc17…d95f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_17.safetensors
safetensors · 325 MB · SHA-256 8f49cd755582…018e · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_18.safetensors
safetensors · 325 MB · SHA-256 aa7ec9c1eacd…2325 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_19.safetensors
safetensors · 325 MB · SHA-256 a57d336aad75…fa79 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_2.safetensors
safetensors · 325 MB · SHA-256 548504b662b2…fe7f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_20.safetensors
safetensors · 325 MB · SHA-256 3e0f75f56ef0…75ac · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_21.safetensors
safetensors · 325 MB · SHA-256 6697a4c4065d…2e08 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_22.safetensors
safetensors · 325 MB · SHA-256 cc56790bfcc2…4a73 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_23.safetensors
safetensors · 325 MB · SHA-256 0403a21ced28…7e3a · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_24.safetensors
safetensors · 325 MB · SHA-256 167692e9300f…ec39 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_25.safetensors
safetensors · 325 MB · SHA-256 89fa61267d6c…fa7f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_26.safetensors
safetensors · 325 MB · SHA-256 6fc0d4712d9c…a88f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_27.safetensors
safetensors · 325 MB · SHA-256 1f05f84b9275…f2a6 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_28.safetensors
safetensors · 325 MB · SHA-256 5c03b684b780…58ea · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_29.safetensors
safetensors · 325 MB · SHA-256 f820ac8deba6…f357 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_3.safetensors
safetensors · 325 MB · SHA-256 8ec4e60c82b8…745d · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_30.safetensors
safetensors · 325 MB · SHA-256 3c6398bc2c17…66f6 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_31.safetensors
safetensors · 325 MB · SHA-256 5b69abb61e37…3d8f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_32.safetensors
safetensors · 325 MB · SHA-256 ea83f1b4b7fa…1494 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_33.safetensors
safetensors · 325 MB · SHA-256 fe6cffd877b6…907b · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_34.safetensors
safetensors · 325 MB · SHA-256 661643bb48cd…89db · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_35.safetensors
safetensors · 325 MB · SHA-256 07fdb196843a…7bef · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_36.safetensors
safetensors · 325 MB · SHA-256 14aaf675f826…9c86 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_37.safetensors
safetensors · 325 MB · SHA-256 f3cc3ad4f428…8bc5 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_38.safetensors
safetensors · 325 MB · SHA-256 53686c2a2b1f…ef02 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_39.safetensors
safetensors · 325 MB · SHA-256 ff3b576b4642…0114 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_4.safetensors
safetensors · 325 MB · SHA-256 be2ee3b0c7ec…6c84 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_40.safetensors
safetensors · 325 MB · SHA-256 fc94dec5b4e5…b4e7 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_41.safetensors
safetensors · 325 MB · SHA-256 08f550430a32…2556 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_42.safetensors
safetensors · 325 MB · SHA-256 3393f112f95c…a31f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_43.safetensors
safetensors · 325 MB · SHA-256 86509ca2be2f…a321 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_44.safetensors
safetensors · 325 MB · SHA-256 80f5f1ae0972…3c9e · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_45.safetensors
safetensors · 325 MB · SHA-256 79c9f82673a2…e041 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_46.safetensors
safetensors · 325 MB · SHA-256 2805129da911…9a73 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_47.safetensors
safetensors · 325 MB · SHA-256 64d99eadaa5b…85db · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_48.safetensors
safetensors · 325 MB · SHA-256 cf79f9cb82e6…db36 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_49.safetensors
safetensors · 325 MB · SHA-256 6941304614cf…c91c · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_5.safetensors
safetensors · 325 MB · SHA-256 b340da0dd678…c859 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_50.safetensors
safetensors · 325 MB · SHA-256 f79fb1df5ebf…d18f · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_51.safetensors
safetensors · 325 MB · SHA-256 5c5a07415677…e265 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_52.safetensors
safetensors · 325 MB · SHA-256 8c1e59f79fa7…d170 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_53.safetensors
safetensors · 325 MB · SHA-256 e308d565a099…f205 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_54.safetensors
safetensors · 325 MB · SHA-256 9f29193dd638…9097 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_55.safetensors
safetensors · 325 MB · SHA-256 a6441cbb9080…bdbd · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_56.safetensors
safetensors · 325 MB · SHA-256 2eb6fda95d3c…2773 · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_57.safetensors
safetensors · 325 MB · SHA-256 0d2b9d9274e0…debb · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_58.safetensors
safetensors · 325 MB · SHA-256 03ecbed33617…dd8d · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_59.safetensors
safetensors · 325 MB · SHA-256 77d7880be8ce…4c7c · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_6.safetensors
safetensors · 325 MB · SHA-256 90565cea773d…018c · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_7.safetensors
safetensors · 325 MB · SHA-256 0e5552a480e6…845e · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_8.safetensors
safetensors · 325 MB · SHA-256 ebdb9896d8ae…ee2b · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/block_9.safetensors
safetensors · 325 MB · SHA-256 3c6c82ed1077…271c · Hugging Face
Descargarqwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_split/non_block.safetensors
safetensors · 155 MB · SHA-256 40163144d4a4…e586 · Hugging Face
DescargarExtractos de fuentes
3 extractos
Extractos de fuentes
3 extractos--- license: apache-2.0 tags: - diffusion-single-file - comfyui - distillation - LoRA - lora - Qwen-Image - Qwen-Image-Edit base_model: - Qwen/Qwen-Image-Edit-2511 pipeline_tags: - image-to-image - text-to-image library_name: diffusers pipeline_tag: image-to-image --- # Qwen-Image-Edit-2511-Lightning ## Model Overview Qwen-Image-Edit-2511-Lightning is a collection of optimized models tailored for image editing tasks, leveraging step distillation and quantization techniques to deliver high-efficiency inference performance. This repository hosts three core model files with distinct characteristics: | Model File Name | Type | Key Features | |-----------------|------|--------------| | `Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors` | 4-step Distilled LoRA | BF16 precision, lightweight, 4-step inference | | `Qwen-Image-Edit-2511-Lightning-4steps-V1.0-fp32.safetensors` | 4-step Distilled LoRA | FP32 precision, high accuracy, 4-step inference | | `qwen_image_edit_2511_fp8_e4m3fn_scaled_lightning.safetensors` | FP8 Quantized | FP8 (e4m3fn scaled) precision, fused with 4-step distilled LoRA, optimized for low-memory deployment | ## Usage Instructions This model suite supports two mainstream usage frameworks, with detailed guides provided below: ### 1. Qwen-Image-Lightning Framework For full documentation on model usage within the Qwen-Image-Lightning ecosystem (including environment setup, inference pipelines, and customization), please refer to: [Qwen-Image-Lightning GitHub Repository](https://github.com/ModelTC/Qwen-Image-Lightning/) ### 2. LightX2V Framework The models are fully compatible with the LightX2V lightweight video/image generation inference framework. For step-by-step usage examples, configuration templates, and performance optimization tips, see: [LightX2V Qwen Image Edit Documentation](https://github.com/ModelTC/LightX2V/blob/main/examples/qwen_image/README.md) ## Key Optimizations - **Step Distillation**: The LoRA models reduce the original inference steps to just 4 steps, achieving significant speedup (≈10x faster than standard 40-step inference) while preserving image editing quality. - **FP8 Quantization**: The quantized base model balances performance and resource efficiency, reducing GPU memory usage by ~50% compared to FP32 while maintaining editing fidelity. ## Support For technical issues, feature requests, or integrat...
Source context: 348817 downloads · 533 likes · Pipeline image-to-image · Library diffusers · Repo lightx2v/Qwen-Image-Edit-2511-Lightning
Source context: 315772 downloads · 486 likes · Pipeline image-to-image · Library diffusers · Repo lightx2v/Qwen-Image-Edit-2511-Lightning
