Description:
This workflow allows you to generate images from a base image and 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.
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
New "add detail" fonction,
Add SeedVarianceEnhancer,
Change upscaler to SeedVR2.
FAQ
Comments (4)
I'm trying to run it, but it gives me this error:loader with Name (Image Saver) Error(s) in loading state_dict for NextDiT: size mismatch for x_embedder.weight: copying a param with shape torch.Size([3840, 64]) from checkpoint, the shape in current model is torch.Size([2304, 64]). size mismatch for x_embedder.bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([2304]).
I launched it, but for some reason the quality is super bad, although I'm using the full model, without GGUF, can you tell me the settings? 👉👈
@JolyBelle My settings are in the workflow. Maybe a problem with the base image? Or your Comfy because i dont have any of this error on mine.
is there a way to set clipSkip ?