¿Tienes un flujo de trabajo de ComfyUI? Obtén un Workflow Doc legible en tu navegador.Haz legible un flujo de trabajo.Pruébalo ahora ↗
The base model is selected just becouse I used it last. Tested on everything from SD1.5 to Flux.2 D
Perfil de ejecución
Descripción de la fuente
I used to use A1111 extension called prompt-travel. I did not find anything like that for ComfyUI so decided to make it myself.
This workflow allows for probably any image generation model since you can just toggle cfg and negative prompt on and off. Some models do not work without cfg and negative prompt while others can or do work without. Turning it on doubles time however.
Settings: on top below the giant wall of text you have the CFG settings and to the left of it settings to video framerate
Then there is positive and negative prompt. I decided that 4 is a good count there. More could be possible but I decided it to be unneeded. It would be possible to even make procedural but even now I have a headache thinking just thinking about the math
Next is timing setting below that. It is the meat of this. It allows 8 different curves and 4 time compression settings. From off to pow(5).
Comentario generado por IA
Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.
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.
Sugerencia · sin verificar
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.
Sugerencia · sin verificar
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.
Sugerencia · sin verificar
Before use, verify that z_image_bf16.safetensors and fairy_forest.safetensors are available in your setup.
Sugerencia · sin verificar
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.
Sugerencia · sin verificar
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuenteExtractos de fuentes
3 extractosSource context: 72 downloads · Type Workflows · Base model ZImageBase
Below that is image count. Self explanatery. It is set to 300 which can take a LOOONG time. Over an hour on a 5090. There should be ETA in console.
To the left of it is Adaptive module settings. For the first time I recommand keeping it off. Turning it on requires at least 41 images. (did not test with less then 60 images)
Below you can set seed for each point. Be carefull some curves just do not work with noise and will result in grey.
Also on top you can select model and even exchange nodes when using model requiring more CLIP models or exchange it entirly for a checkpoint loader when you want to use SDXL or simillar.
The right side:
Be carefull. The right side can be laggy after generationg. On top you have your video output, on the bottom you have all imades it generates (the source of lag) and in the middle you have a graph which shows you the density of output. Does not show exactly reality when adaptive stages are off becouse the circullar corners.
Requisito de VRAM estimado
Estimación no disponible
7,80 GB en 2 de 4 archivos de modelos. Total de archivos de modelos + 25 % de sobrecarga de carga + 2 GB de margen de ejecución, redondeado hacia arriba.
Requisitos
6 requisitosVAE · 320 MB · Hugging Face · Comfy-Org/z_image_turbo
Fuentes posibles
LoRA · Hugging Face · DavidBaloches/Fairy_Forest
Text encoder · 7.49 GB · Hugging Face · Comfy-Org/z_image_turbo
Fuentes posibles
Checkpoint · Civitai · 2342797
Fuentes posibles
Paquete de nodos · Registry
Paquete de nodos · Registry
Source context: 57 downloads · Type Workflows · Base model ZImageBase
Source context: 55 downloads · Type Workflows · Base model ZImageBase
