ComfyUI Node
Eric Qwen Grounded Generate
A ComfyUI node in Eric/QwenImage with 16 inputs and 1 output.
Eric Qwen Grounded Generate
- pipeline
- ref_image_1
- ref_image_2
- ref_image_3
- ref_image_4
- image
◄grounded_prompt►
◄aspect_ratio1:1►
◄output_mp2.00►
◄ref_modevl_only►
◄negative_prompt►
◄steps8►
◄true_cfg_scale4.0►
◄seed0►
◄custom_width1920►
◄custom_height1080►
◄add_generation_prefixfalse►
CategoryEric/QwenImage
Inputs (16)
| Name | Type | Default | Description |
|---|---|---|---|
| pipeline | QWEN_EDIT_PIPELINE | — | |
| grounded_prompt | STRING | Rich prompt from EricGenSearcherNode (or any detailed prompt). | |
| ref_image_1 | IMAGE | Primary visual reference image. | |
| aspect_ratio | COMBO | 1:1 | Output aspect ratio. 16:9 = landscape (~1920×1080 at 2MP) 9:16 = portrait (~1080×1920 at 2MP) 1:1 = square (~1448×1448 at 2MP) custom = use output_width / output_height exactly |
| output_mp | FLOAT | 2.000.25–16 | Output megapixels: 0.5 MP → quick test 1.0 MP → ~1024×1024 (1:1) 2.0 MP → ~1448×1448 (1:1) ~1920×1080 (16:9) 4.0 MP → ~2048×2048 (1:1) (slow) Ignored when aspect_ratio=custom. |
| ref_mode | COMBO | vl_only | How reference images condition the generation: vl_only (RECOMMENDED for web images): All refs → VL/semantic path only (REF=False). Model understands subject appearance but generates at full quality without pixel-level constraints. Best when references are web search thumbnails. primary_ref: ref_image_1 → VL+REF (pixel level). Others → VL only. Use when ref_image_1 is a high-quality photo. all_ref: All images → VL+REF. Only use with curated high-quality inputs. NOT recommended for web search results. |
| ref_image_2opt | IMAGE | Optional 2nd reference image. | |
| ref_image_3opt | IMAGE | Optional 3rd reference image. | |
| ref_image_4opt | IMAGE | Optional 4th reference image. | |
| negative_promptopt | STRING | — | |
| stepsopt | INT | 81–100 | 8 for lightning LoRA, 50 for base model. |
| true_cfg_scaleopt | FLOAT | 4.01–20 | — |
| seedopt | INT | 00–18446744073709550000 | — |
| custom_widthopt | INT | 1920256–8192 | Used only when aspect_ratio=custom. |
| custom_heightopt | INT | 1080256–8192 | Used only when aspect_ratio=custom. |
| add_generation_prefixopt | BOOLEAN | false | Prepend a directive telling the model to create a new image. OFF (default): use the grounded prompt as-is. The Qwen-Image model understands image generation from detailed prompts. ON: prepends 'Generate a completely new image...' May fight against the model's edit-focused fine-tuning. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |