Prompt and seed travel — v1.0

Prompt and seed travel — v1.0 is a ComfyUI workflow for generating images with prompts and seeds that change over time; you set prompts, timing curves, per-point seeds, image count, video framerate, CFG options, and a model, and it produces generated images, a video, and an out­-

Choose from eight timing curves and four time-compression settings, ranging from off to pow(5).

The output area shows video at the top, generated images at the bottom, and an output-density graph in the middle.

Some timing curves may produce grey results with noise, and the output-density graph may not exactly reflect the output when adaptive stages are off.

Vorschlag · nicht geprüft

Set positive and negative prompts, CFG controls, video framerate, timing choices, per-point seeds, and image-count controls.

The image-count setting controls how many images are generated.

Version v1.0 is published by MkDaniel and lists ZImageBase as its base model.

The listed model files are qwen_3_4b.safetensors, ae.safetensors, z_image_bf16.safetensors, and fairy_forest.safetensors.

The workflow requires two node packs: comfyui-mxtoolkit and more_math.

Set the CFG and negative-prompt toggles according to the selected model; some models require them, while others can work without them.

Vorschlag · nicht geprüft

Select a model at the top; swap nodes for models requiring more CLIP models, or use a checkpoint loader for SDXL or similar models.

Keep the Adaptive module off initially; enabling it requires at least 41 images, and use with fewer than 60 images is untested.

Vorschlag · nicht geprüft

Before use, verify that z_image_bf16.safetensors and fairy_forest.safetensors are available in your setup.

Vorschlag · nicht geprüft

Enabling CFG and negative-prompt controls is reported to double generation time; 300 images is reported to take over an hour on a 5090, and both timings are untested.

Vorschlag · nicht geprüft