Description:
This workflow allows you to generate images from text. It is optimized to integrate all metadata for simplified online publishing.
It integrates an upscaler/sampler which, although it takes longer than a classic upscaler, allows for much better quality.
You will find a step-by-step guide to using this workflow here: link
Resources you need:
📂Files for "base" version :
Model : z_image_turbo_bf16.safetensors
in ComfyUI\models\diffusion_models
CLIP : qwen_3_4b.safetensors
in ComfyUI\models\clip
📂Files for GGUF version :
Model : Q8, Q6, Q5, Q4, Q3
in ComfyUI\models\unet
CLIP : Q6
in ComfyUI\models\clip
📂Common Files
VAE : ae.safetensors
in ComfyUI\models\vae
ANY upscale model :
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in ComfyUI\models\upscale_models
📦Custom Nodes :
Description
Change upscaler to SeedVR2
FAQ
Comments (9)
what's the purpose of the negative prompt? with cfg=1 with zIT .... that gets zeroed out, no?
That's perfectly correct. I implemented the negative prompt in anticipation of the "non-turbo" Z-Image output, which will take the negative prompt and CFG>1.
I have many different workflows, and it's better if I don't have to redo everything with each update. I actually specified this in the workflow guide.
@UmeAiRT makes sense. thanks!
I don't suppose anyone knows why my images come out grainy and fried?
Euler Beta (or anything else)
Steps 8-10
CFG 1 (or anything else)
MODEL: z_image_turbo_bf16
VAE: ae (or z-image vae)
CLIP: qwen_3_4b
This is not related to any specified workflow either, and I've had it working fine before.
I just tested this workflow, and when I use "add details," it makes the image noisy with distortions. This is inherent to using a detailer, I get decent result with detail strength at 0.10
I can't see any slider. How to enable that?
Can anyone guide me I am using V1.2 and I can't see sliders....
If you are unable to see sliders do this:
Open ui_mixlab.js with notepad, visual studio or other similar programs and replace these lines
const orig = node.__proto__.onDrawForeground
to
const orig = node.onDrawForeground ?? node.__proto__.onDrawForeground;
Source: Search this on google. Nodes missing content (Sliders, Values...)
I can't share direct link.
this is happening because of comfyui update. Thanks