Qwen Image Edit

by Comfy-Org / QuantStack · ★★★★½ 4.8 · 275K downloads · — · qwen-image

Install with mods

mods install qwen-image-edit

⚡ Running mods install qwen-image-edit without --variant auto-selects the best variant for your GPU VRAM.

Available variants: bf16, fp8-hq, fp8-mixed, fp8, nvfp4, 2512-bf16, 2512-fp8, gguf-q8-0, gguf-q6-k, gguf-q5-k-m, gguf-q5-k-s, gguf-q5-0, gguf-q5-1, gguf-q4-k-m, gguf-q4-k-s, gguf-q4-0, gguf-q4-1, gguf-q3-k-m, gguf-q3-k-s, gguf-q2-k
mods install qwen-image-edit --variant bf16

About

AI-powered image editing model based on Qwen 2.5 VL architecture.

Supports outpainting, format/ratio changes, AI scene generation, and in-place enhancement.

Best with 8 steps using Lightning LoRA, euler sampler, CFG 1.0.

Available as native safetensors (bf16/fp8) or GGUF quantizations (Q2_K through Q8_0).

Variants

Variant	Format	Size	VRAM	Install
bf16 ⓘ	safetensors	43.9 GB	40+ GB	`mods install qwen-image-edit --variant bf16`
fp8-hq ⓘ	safetensors	24.4 GB	24+ GB	`mods install qwen-image-edit --variant fp8-hq`
fp8-mixed ⓘ	safetensors	22.0 GB	24+ GB	`mods install qwen-image-edit --variant fp8-mixed`
fp8 ⓘ	safetensors	21.9 GB	20+ GB	`mods install qwen-image-edit --variant fp8`
nvfp4 ⓘ	safetensors	21.3 GB	16+ GB	`mods install qwen-image-edit --variant nvfp4`
2512-bf16 ⓘ	safetensors	43.9 GB	40+ GB	`mods install qwen-image-edit --variant 2512-bf16`
2512-fp8 ⓘ	safetensors	21.9 GB	20+ GB	`mods install qwen-image-edit --variant 2512-fp8`
gguf-q8-0 ⓘ	gguf	23.4 GB	24+ GB	`mods install qwen-image-edit --variant gguf-q8-0`
gguf-q6-k ⓘ	gguf	18.0 GB	20+ GB	`mods install qwen-image-edit --variant gguf-q6-k`
gguf-q5-k-m ⓘ	gguf	16.0 GB	16+ GB	`mods install qwen-image-edit --variant gguf-q5-k-m`
gguf-q5-k-s ⓘ	gguf	15.1 GB	16+ GB	`mods install qwen-image-edit --variant gguf-q5-k-s`
gguf-q5-0 ⓘ	gguf	15.5 GB	16+ GB	`mods install qwen-image-edit --variant gguf-q5-0`
gguf-q5-1 ⓘ	gguf	16.5 GB	16+ GB	`mods install qwen-image-edit --variant gguf-q5-1`
gguf-q4-k-m ⓘ	gguf	14.1 GB	12+ GB	`mods install qwen-image-edit --variant gguf-q4-k-m`
gguf-q4-k-s ⓘ	gguf	13.0 GB	12+ GB	`mods install qwen-image-edit --variant gguf-q4-k-s`
gguf-q4-0 ⓘ	gguf	12.8 GB	12+ GB	`mods install qwen-image-edit --variant gguf-q4-0`
gguf-q4-1 ⓘ	gguf	13.7 GB	12+ GB	`mods install qwen-image-edit --variant gguf-q4-1`
gguf-q3-k-m ⓘ	gguf	10.4 GB	10+ GB	`mods install qwen-image-edit --variant gguf-q3-k-m`
gguf-q3-k-s ⓘ	gguf	9.6 GB	10+ GB	`mods install qwen-image-edit --variant gguf-q3-k-s`
gguf-q2-k ⓘ	gguf	7.6 GB	8+ GB	`mods install qwen-image-edit --variant gguf-q2-k`

Dependencies

📦 These models are automatically installed when you run mods install qwen-image-edit. No extra steps needed — mods resolves and downloads all dependencies for you.

vae Qwen Image VAE Qwen Image Edit requires the Qwen-specific VAE text encoder Qwen 2.5 VL 7B Text Encoder Qwen 2.5 VL 7B text/vision encoder for prompt processing