Moody Base + Turbo Image Generator

Generate an image or batch from text using the source's fixed Moody Base/Turbo checkpoint pair. A Base pass establishes composition, the latent is resized, Turbo refines it, and tiled diffusion produces the enlarged result. The Pipe returns only the finished image collection, without permanently saving images through the source SaveImage node. For a first run, replace the positive prompt with your subject, composition, lighting and style, and review the negative prompt. Keep the 640 × 960 starting size, refinement scale of 1.7, enlargement factor of 2 and supplied sampling defaults. No uploaded image is required. Final dimensions depend on both scale factors and latent-size rounding; final enlargement applies to the decoded Turbo result. Scale factors below 1 reduce dimensions. Larger dimensions, scales and image counts increase memory and processing requirements. The negative prompt affects the Base pass only. Turbo refinement, tiled enlargement and face refinement use zeroed negative conditioning. Enlargement normally reuses the main positive prompt. Enable Use separate enlargement prompt and edit Enlargement prompt to replace it for tiled redraw. Higher enlargement denoise permits more changes to existing details and content. Advanced sampling controls belong to separate stages. Base defaults use a 17-step schedule starting at 0 and stopping at 12, retaining noise for refinement. Turbo defaults use an 11-step schedule beginning at 5 and completing the schedule. These schedule lengths are not the number of iterations each pass executes. When changing them, review the corresponding start and end boundaries; keep the Turbo starting boundary below its schedule length. Each stage has its own seed. -1 randomizes that stage on each run; use explicit seeds for all active stages when retaining their random choices. Enlargement uses automatically calculated tile dimensions that depend on the decoded image size and enlargement factor. Tile batch size controls how many redraw tiles are processed together, separate from Image count, and can change results. Tile padding controls redraw context, while the automatic dimension formulas retain a fixed 96-pixel allowance. Seam repair starts at None. Select a repair mode before adjusting its denoise, blur or padding; Seam band width applies to Band Pass repair. Face refinement is optional and initially bypassed. Enable it to detect and redraw faces, then replace the portrait-specific Face prompt for your subject. Face denoise controls redraw strength. Detection threshold and minimum size determine which detections are accepted; crop context, region expansion and feathering control the processed regions and their blending. Detection may miss small or obscured faces. Face sampling and cycle controls apply only when this stage is enabled. Skin contrast finishing is optional and initially bypassed. Enable it to apply the fixed skin contrast model, then adjust Skin contrast strength. With Normal blending, 0 keeps the image before finishing and 1 uses the full finishing result; strength has no effect while finishing is bypassed. Other blend modes can alter the image even with finishing bypassed because they combine two identical inputs differently. The source's manual mask detailer and native editor bridge remain hidden and bypassed. This Pipe does not provide a live paint-mask session or portable manual mask refinement. Optional finishing stages process the generated image and still run the upstream generation and enlargement stages. Model selections are fixed to the source's Moody checkpoints; stock Z-Image catalog entries do not establish that those specific files are installed.

Generate an image or batch from text using the source's fixed Moody Base/Turbo checkpoint pair. A Base pass establishes composition, the latent is resized, Turbo refines it, and tiled diffusion produces the enlarged result. The Pipe returns only the finished image collection, without permanently saving images through the source SaveImage node. For a first run, replace the positive prompt with your subject, composition, lighting and style, and review the negative prompt. Keep the 640 × 960 starting size, refinement scale of 1.7, enlargement factor of 2 and supplied sampling defaults. No uploaded image is required. Final dimensions depend on both scale factors and latent-size rounding; final enlargement applies to the decoded Turbo result. Scale factors below 1 reduce dimensions. Larger dimensions, scales and image counts increase memory and processing requirements. The negative prompt affects the Base pass only. Turbo refinement, tiled enlargement and face refinement use zeroed negative conditioning. Enlargement normally reuses the main positive prompt. Enable Use separate enlargement prompt and edit Enlargement prompt to replace it for tiled redraw. Higher enlargement denoise permits more changes to existing details and content. Advanced sampling controls belong to separate stages. Base defaults use a 17-step schedule starting at 0 and stopping at 12, retaining noise for refinement. Turbo defaults use an 11-step schedule beginning at 5 and completing the schedule. These schedule lengths are not the number of iterations each pass executes. When changing them, review the corresponding start and end boundaries; keep the Turbo starting boundary below its schedule length. Each stage has its own seed. -1 randomizes that stage on each run; use explicit seeds for all active stages when retaining their random choices. Enlargement uses automatically calculated tile dimensions that depend on the decoded image size and enlargement factor. Tile batch size controls how many redraw tiles are processed together, separate from Image count, and can change results. Tile padding controls redraw context, while the automatic dimension formulas retain a fixed 96-pixel allowance. Seam repair starts at None. Select a repair mode before adjusting its denoise, blur or padding; Seam band width applies to Band Pass repair. Face refinement is optional and initially bypassed. Enable it to detect and redraw faces, then replace the portrait-specific Face prompt for your subject. Face denoise controls redraw strength. Detection threshold and minimum size determine which detections are accepted; crop context, region expansion and feathering control the processed regions and their blending. Detection may miss small or obscured faces. Face sampling and cycle controls apply only when this stage is enabled. Skin contrast finishing is optional and initially bypassed. Enable it to apply the fixed skin contrast model, then adjust Skin contrast strength. With Normal blending, 0 keeps the image before finishing and 1 uses the full finishing result; strength has no effect while finishing is bypassed. Other blend modes can alter the image even with finishing bypassed because they combine two identical inputs differently. The source's manual mask detailer and native editor bridge remain hidden and bypassed. This Pipe does not provide a live paint-mask session or portable manual mask refinement. Optional finishing stages process the generated image and still run the upstream generation and enlargement stages. Model selections are fixed to the source's Moody checkpoints; stock Z-Image catalog entries do not establish that those specific files are installed.