ComfyUI Node
ArchAi3D_Qwen_Encoder_Simple
A ComfyUI node in ArchAi3d/Qwen with 15 inputs and 3 outputs.
ArchAi3D_Qwen_Encoder_Simple
- clip
- vae
- image1_vl
- image2_vl
- image3_vl
- image1_latent
- image2_latent
- image3_latent
- conditioning
- latent
- formatted_prompt
◄prompt—►
◄system_prompt►
◄conditioning_strength1.00►
◄image1_latent_strength1.00►
◄image2_latent_strength1.00►
◄image3_latent_strength1.00►
◄debug_modefalse►
CategoryArchAi3d/Qwen
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | Qwen-VL CLIP model for tokenization and encoding | |
| prompt | STRING | User prompt text (vision tokens added automatically) | |
| system_prompt | STRING | Optional system prompt (uses ChatML format: <|im_start|>system...when provided) | |
| conditioning_strength | FLOAT | 1.000–2 | Global conditioning strength multiplier (1.0=normal, >1.0=stronger, <1.0=weaker). Acts like CFG weight. |
| image1_latent_strength | FLOAT | 1.000–2 | [EXPERIMENTAL] Multiplies image1 reference latent values (1.0=normal, >1.0=stronger, <1.0=weaker) |
| image2_latent_strength | FLOAT | 1.000–2 | [EXPERIMENTAL] Multiplies image2 reference latent values (1.0=normal, >1.0=stronger, <1.0=weaker) |
| image3_latent_strength | FLOAT | 1.000–2 | [EXPERIMENTAL] Multiplies image3 reference latent values (1.0=normal, >1.0=stronger, <1.0=weaker) |
| debug_mode | BOOLEAN | false | Print detailed info to console (conditioning shapes, strengths applied, etc.) |
| vaeopt | VAE | VAE for encoding reference latents (optional, needed for latent outputs) | |
| image1_vlopt | IMAGE | Image 1 for Qwen-VL vision encoder (RGB channels only, no resize) | |
| image2_vlopt | IMAGE | Image 2 for Qwen-VL vision encoder (RGB channels only, no resize) | |
| image3_vlopt | IMAGE | Image 3 for Qwen-VL vision encoder (RGB channels only, no resize) | |
| image1_latentopt | IMAGE | Image 1 for VAE encoding as reference latent (RGB only, standard 4D format) | |
| image2_latentopt | IMAGE | Image 2 for VAE encoding as reference latent (RGB only, standard 4D format) | |
| image3_latentopt | IMAGE | Image 3 for VAE encoding as reference latent (RGB only, standard 4D format) |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| conditioning | CONDITIONING | Encoded conditioning with vision tokens and reference latents |
| latent | LATENT | image1_latent encoded output in standard format (compatible with VAEDecode) |
| formatted_prompt | STRING | Final formatted prompt sent to the model (includes vision tokens and ChatML) |