ComfyUI Node
RH Qwen-Image 2.1 Diffusers
Runs the official diffusers Qwen-Image 2.1 pipeline (Qwen3-VL text encoder + single-stream block-causal transformer + AutoencoderKLQwenImage21). One node covers all four official modes: text-to-image (no image inputs), single-image editing, multi-reference composition (up to 10 images, order matters) and RGBA transparency generation. Weights stream through ComfyUI DynamicVRAM (ModelPatcher + load_models_gpu) per stage.
RH Qwen-Image 2.1 Diffusers
- image_1
- image_2
- image_3
- image_4
- image_5
- image_6
- image_7
- image_8
- image_9
- image_10
- images
- alpha
◄prompt►
◄true_cfg_scale1.0►
◄num_inference_steps40►
◄output_resolution1024►
◄width0►
◄height0►
◄seed0►
◄use_kv_cachetrue►
◄negative_prompt►
CategoryRunningHub/Qwen-Image
Inputs (19)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Prompt guiding the generation. The pipeline wraps it in the official chat template before the Qwen3-VL encoder. | |
| true_cfg_scale | FLOAT | 1.01–10 | Classifier-free guidance scale. Default 1.0 = no guidance (official recommendation). Needs a non-empty negative prompt to activate; doubles the compute per step when enabled. |
| num_inference_steps | INT | 404–100 | Denoising steps. Official recommendation is 40. |
| output_resolution | INT | 1024256–2048 | Target side length. Text-to-image derives a width/height around it; image-conditioned mode derives them from the last condition image's aspect ratio. Rounded to multiples of 32. Use width/height overrides for native-2K ratios (e.g. 2752x1536 16:9). |
| width | INT | 00–2752 | Explicit output width. 0 = derive from output_resolution / condition image aspect ratio. Official 2K 16:9 is 2752. |
| height | INT | 00–2752 | Explicit output height. 0 = derive from output_resolution / condition image aspect ratio. Official 2K 16:9 is 1536. |
| seed | INT | 00–9223372036854776000 | Random seed. Same settings + same seed reproduce the image. |
| use_kv_cache | BOOLEAN | true | Cache text/condition keys and values after the first step (official default). Disabling it recomputes the whole prefix every step (slower). |
| image_1opt | IMAGE | Condition image slot 1/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_2opt | IMAGE | Condition image slot 2/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_3opt | IMAGE | Condition image slot 3/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_4opt | IMAGE | Condition image slot 4/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_5opt | IMAGE | Condition image slot 5/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_6opt | IMAGE | Condition image slot 6/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_7opt | IMAGE | Condition image slot 7/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_8opt | IMAGE | Condition image slot 8/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_9opt | IMAGE | Condition image slot 9/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| image_10opt | IMAGE | Condition image slot 10/10. Leave all empty for text-to-image; one image = single-image editing; up to ten = official multi-reference composition (a batched input contributes all its frames in order; later blocks attend to earlier ones, so order matters). | |
| negative_promptopt | STRING | Negative prompt. Only takes effect together with true_cfg_scale > 1 (the model is trained to sample without guidance). |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| alpha | MASK | — |