ComfyUI Node
Eric Qwen-Edit Multi-Image Fusion
A ComfyUI node in Eric Qwen-Edit with 23 inputs and 1 output.
Eric Qwen-Edit Multi-Image Fusion
- pipeline
- image_1
- image_2
- image_3
- image_4
- image
◄promptAll subjects are sitting together on a couch, looking at the camera.►
◄composition_modegroup►
◄subject_labelperson►
◄main_imageimage_1►
◄vae_target_size0►
◄vl_1true►
◄vl_2true►
◄vl_3true►
◄vl_4true►
◄ref_1true►
◄ref_2true►
◄ref_3false►
◄ref_4false►
◄negative_prompt►
◄steps8►
◄true_cfg_scale4.0►
◄seed0►
◄max_mp8.0►
CategoryEric Qwen-Edit
Inputs (23)
| Name | Type | Default | Description |
|---|---|---|---|
| pipeline | QWEN_EDIT_PIPELINE | — | |
| image_1 | IMAGE | First input image (Picture 1) — default main image | |
| image_2 | IMAGE | Second input image (Picture 2) | |
| prompt | STRING | All subjects are sitting together on a couch, looking at the camera. | In 'raw' mode: write the full prompt referencing Picture 1, Picture 2, etc. In other modes: describe the desired scene/action (image references are auto-added). |
| composition_mode | COMBO | group | group: place subjects side-by-side with positions | scene: use Picture 1 as background, place others into it | merge: fuse features into one subject | raw: your prompt exactly as-is |
| image_3opt | IMAGE | Optional third image (Picture 3) | |
| image_4opt | IMAGE | Optional fourth image (Picture 4) | |
| subject_labelopt | STRING | person | What to call each subject in auto-generated prompts (e.g. 'person', 'woman', 'character', 'bear', 'product') |
| main_imageopt | COMBO | image_1 | Which image is the primary reference. Its VAE latent seeds the denoising process for strongest reconstruction. |
| vae_target_sizeopt | INT | 00–2048 | Fixed resolution for VAE encoding. 0 (default) = encode refs at output resolution (matches Edit node behavior, best for high-res). Set to e.g. 1024 to force all refs to ~1MP (only useful at low output res). |
| vl_1opt | BOOLEAN | true | Include image_1 in VL/semantic path (text encoder understands its content) |
| vl_2opt | BOOLEAN | true | Include image_2 in VL/semantic path |
| vl_3opt | BOOLEAN | true | Include image_3 in VL/semantic path |
| vl_4opt | BOOLEAN | true | Include image_4 in VL/semantic path |
| ref_1opt | BOOLEAN | true | Include image_1 in VAE/ref path (pixel-level latent reference) |
| ref_2opt | BOOLEAN | true | Include image_2 in VAE/ref path |
| ref_3opt | BOOLEAN | false | Include image_3 in VAE/ref path (default False — VL-only for secondary images) |
| ref_4opt | BOOLEAN | false | Include image_4 in VAE/ref path (default False — VL-only for secondary images) |
| negative_promptopt | STRING | What to avoid in the output | |
| stepsopt | INT | 81–100 | Inference steps (8 for lightning LoRA, 50 for base model) |
| true_cfg_scaleopt | FLOAT | 4.01–20 | True CFG scale (main quality control) |
| seedopt | INT | 00–18446744073709550000 | Random seed |
| max_mpopt | FLOAT | 8.00.5–16 | Max output megapixels. VAE refs scale to match output resolution. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |