Qwen-Image-2.1 Image Edit 6step

Note: All model files and custom nodes below must be downloaded via the client. If you do not have the client, Download >>>

This model is released under the strict Qwen Research License Agreement, which restricts usage to academic and research purposes only and prohibits any commercial use. Qwen-Image-2.1 is an image generation model built on a lightweight Diffusion Transformer (DiT) architecture, featuring native transparent image generation capability that allows it to directly output PNG images with alpha channels without requiring additional processing. It is important to note that this model supports a maximum of only 1 to 3 reference images for editing tasks, and attempting to input more than three reference images will result in degraded or failed performance

Qwen-Image-2.1 VAE >1 files

Name	Size	Target Dir
qwen_image_2.1_vae_bf16.safetensors	675.51 MB	vae

Qwen-Image-2.1 >2 files

Name	Size	Target Dir
qwen_image_2.1_int8_convrot.safetensors	7.26 GB	diffusion_models
qwen_image_2.1_bf16.safetensors	14.23 GB	diffusion_models

Qwen-Image-2.1-viggle-turbo >5 files

Name	Size	Target Dir
Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors	339.83 MB	loras
Qwen-Image-2.1-viggle-turbo-v0.2-5step-lora-r128.safetensors	679.6 MB	loras
Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r128.safetensors	679.6 MB	loras
Qwen-Image-2.1-viggle-turbo-v0.2-5step-lora-r256.safetensors	1.36 GB	loras
Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors	1.36 GB	loras

Qwen-Image-2.1 text_encoders >7 files

Name	Size	Target Dir
qwen3vl_8b_w4a8.safetensors	6.31 GB	text_encoders
qwen3.5_9b_qwen_image_2.1_pe_i2i_w4a8.safetensors	6.72 GB	text_encoders
qwen3.5_9b_qwen_image_2.1_pe_t2i_w4a8.safetensors	6.72 GB	text_encoders
qwen3vl_8b_int8_convrot.safetensors	9.35 GB	text_encoders
qwen3.5_9b_qwen_image_2.1_pe_i2i.int8_convrot.safetensors	9.47 GB	text_encoders
qwen3.5_9b_qwen_image_2.1_pe_t2i.int8_convrot.safetensors	9.47 GB	text_encoders
qwen3vl_8b_bf16.safetensors	17.53 GB	text_encoders