TenserTensor
22c3d146bd
Implement post-production processing nodes: - add_film_grain.py: procedural film grain effect - apply_lut.py: LUT-based color grading - image_enhancer.py: comprehensive image adjustments (brightness, contrast, gamma, hue, saturation, sharpness, posterize, solarize) - postproduction.py: all-in-one pipeline (LUT + film grain + upscaling) - postproduction_advanced.py: extended pipeline with image enhancement controls - quick_image_upscaler.py: simple tiled AI upscaler Add markdown documentation for all post-production nodes
2.2 KiB
2.2 KiB
TT CLIP Text Encode SDXL TT_ClipTextEncodeSdxl
This description was generated with AI assistance. If you spot any errors, please create an issue on GitHub.
SDXL text encoder with separate CLIP-L and CLIP-G prompt inputs and conditioning parameters.
Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
clip |
CLIP | Yes | CLIP text encoder (dual CLIP-L + CLIP-G) |
clip_l_positive |
STRING | Yes | CLIP-L positive prompt (multiline) |
clip_g_positive |
STRING | Yes | CLIP-G positive prompt (multiline) |
clip_l_negative |
STRING | Yes | CLIP-L negative prompt (multiline) |
clip_g_negative |
STRING | Yes | CLIP-G negative prompt (multiline) |
ascore_positive |
FLOAT | Yes | Aesthetic score for positive (0.0-1000.0, default: 9.0) |
ascore_negative |
FLOAT | Yes | Aesthetic score for negative (0.0-1000.0, default: 6.0) |
width |
INT | Yes | Image width for conditioning (default: 512) |
height |
INT | Yes | Image height for conditioning (default: 512) |
target_width |
INT | Yes | Target width for conditioning (default: 512) |
target_height |
INT | Yes | Target height for conditioning (default: 512) |
Outputs
| Parameter | Type | Description |
|---|---|---|
POSITIVE |
CONDITIONING | Positive conditioning with aesthetic score and dimensions |
NEGATIVE |
CONDITIONING | Negative conditioning with aesthetic score and dimensions |
Usage
Encode text prompts for SDXL with separate control over CLIP-L and CLIP-G inputs, aesthetic scores, and target dimensions. The aesthetic scores and dimensions are embedded into the conditioning to guide the generation process.