This workflow uses a light iterative latent upscale pass to significantly increase LoRA influence and overall detail quality on Z-Image-Turbo. Uses Impact pack and RGThree.
Runtime profile
Source description
This workflow uses a light iterative latent upscale pass to significantly increase LoRA influence and overall detail quality on Z-Image-Turbo. Uses Impact pack and RGThree.
Generate base image normally (8–12 steps)
Connect to Iterative Latent Upscale (Impact Pack):
Upscale factor: 1.1–2
Steps: 1 to 3. Depends what effect you want. I run with 1 most of the time
Denoise: 0.22–0.49
Use same model, LoRA(s) and strength as base generation
Main effects
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this ZImageTurbo workflow to apply an iterative latent upscale to a normally generated base image, reusing the same model, LoRA(s), and strength to produce an upscaled image.
Generate the base image normally in 8–12 steps, then connect it to Iterative Latent Upscale (Impact Pack).
The described results are stronger LoRA style or character expression, sharper details and textures, and better facial features and micro-details without major composition changes.
The workflow declares these node packs: comfyui_essentials, comfyui-impact-pack, and rgthree-comfy.
Named model files include ae.safetensors (VAE), qwen_3_4b.safetensors (text encoder), Soyjak 2 z.safetensors (LoRA), and z_image_turbo_bf16.safetensors (UNet).
Try an upscale factor of 1.1–2 and denoise of 0.22–0.49; choose 1–3 steps for the effect you want. The author says they usually use 1 step.
Suggestion
The workflow names Soyjak 2 z.safetensors as a LoRA; confirm that this is the file you want to use.
Suggestion
No license is listed; check the applicable usage terms before reuse.
Suggestion
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 325 downloads · Type Workflows · Base model ZImageTurbo
Much stronger LoRA style/character expression
Sharper fine details and textures
Better facial features and micro-details without major composition changes
Remaining hardware or download-size estimates are not available yet.
Requirements
VAE · 320 MB · SAFETENSORS · Civitai · 1223425
Text encoder · 7.49 GB · SAFETENSORS · Civitai · 2168935
Source context: 324 downloads · Type Workflows · Base model ZImageTurbo
Source context: 274 downloads · Type Workflows · Base model ZImageTurbo
Soyjak 2 z.safetensors
Not resolvedLoRA · Unknown
Checkpoint · 11.5 GB · SAFETENSORS · bf16 · Civitai · 2168935
Node pack · Registry
comfyui-impact-pack
FoundNode pack · Registry
rgthree-comfy
FoundNode pack · Registry