This node is specifically designed for the SDXL Refiner model to convert text prompts into conditioning information by incorporating aesthetic scores and dimensional information to enhance the conditions for generation tasks, thereby improving the final refinement effect. It acts like a professional art director, not only conveying your creative intent but also injecting precise aesthetic standards and specification requirements into the work.

About SDXL Refiner

SDXL Refiner is a specialized refinement model that focuses on enhancing image details and quality based on the SDXL base model. This process is like having an art retoucher:

  1. First, it receives preliminary images or text descriptions generated by the base model
  2. Then, it guides the refinement process through precise aesthetic scoring and dimensional parameters
  3. Finally, it focuses on processing high-frequency image details to improve overall quality

Refiner can be used in two ways:

  • As a standalone refinement step for post-processing images generated by the base model
  • As part of an expert integration system, taking over processing during the low-noise phase of generation

Inputs

Parameter NameData TypeInput TypeDefault ValueValue RangeDescription
clipCLIPRequired--CLIP model instance used for text tokenization and encoding, the core component for converting text into model-understandable format
ascoreFLOATOptional6.00.0-1000.0Controls the visual quality and aesthetics of generated images, similar to setting quality standards for artwork:
- High scores(7.5-8.5): Pursues more refined, detail-rich effects
- Medium scores(6.0-7.0): Balanced quality control
- Low scores(2.0-3.0): Suitable for negative prompts
widthINTRequired102464-16384Specifies output image width (pixels), must be multiple of 8. SDXL performs best when total pixel count is close to 1024×1024 (about 1M pixels)
heightINTRequired102464-16384Specifies output image height (pixels), must be multiple of 8. SDXL performs best when total pixel count is close to 1024×1024 (about 1M pixels)
textSTRINGRequired--Text prompt description, supports multi-line input and dynamic prompt syntax. In Refiner, text prompts should focus more on describing desired visual quality and detail characteristics

Outputs

Output NameData TypeDescription
CONDITIONINGCONDITIONINGRefined conditional output containing integrated encoding of text semantics, aesthetic standards, and dimensional information, specifically for guiding SDXL Refiner model in precise image refinement

Notes

  1. This node is specifically optimized for the SDXL Refiner model and differs from regular CLIPTextEncode nodes
  2. An aesthetic score of 7.5 is recommended as the baseline, which is the standard setting used in SDXL training
  3. All dimensional parameters must be multiples of 8, and total pixel count close to 1024×1024 (about 1M pixels) is recommended
  4. The Refiner model focuses on enhancing image details and quality, so text prompts should emphasize desired visual effects rather than scene content
  5. In practical use, Refiner is typically used in the later stages of generation (approximately the last 20% of steps), focusing on detail optimization