Z-Image Image-to-Image — ComfyUI workflow

Re-render a source image with a Z-Image checkpoint at a chosen denoise strength: the 6B base (CFG and negative prompt) or a Civitai Turbo finetune on its 8-step schedule, with an optional Z-Image LoRA. No upstream Z-Image image-to-image template exists at Comfy-Org/workflow_templates@aaac56dd, so the graph is this catalog's chroma-img2img shape (LoadImage, VAEEncode, KSampler at a denoise below 1) with the Z-Image model stack and sampler values of templates/image_z_image.json (res_multistep + simple, 25 steps, CFG 4, ModelSamplingAuraFlow shift 3) and templates/image_z_image_turbo.json (8 steps, CFG 1, negative zeroed); the source is bounded to a longest side of 1024 with the ImageScaleToMaxDimension node templates/image_z_image_turbo_fun_union_controlnet.json uses. Choosing a Turbo checkpoint selects the Turbo schedule through checkpoint_profile.

15Graph nodes

14Node classes

10Inputs

10Models

Tags: zimagerunpod-serverlessvolume-backedimage-to-image

Inputs (10)#

The typed parameter surface callers bind when they request this workflow. Enum options and numeric bounds are the values the workflow document declares.

promptstringrequireddefault a close-up photograph of the same scene at golden hour, warm light, natural colours, sharp focus

Positive prompt describing the re-rendered image in natural prose

negative_promptstringdefault

Negative prompt, honoured by the base checkpoint (CFG-guided; the upstream base template leaves it empty). A Turbo checkpoint samples at CFG 1 with the negative zeroed (ConditioningZeroOut, as the upstream Turbo template does), so this text is not encoded for it.

checkpointenumdefault zimage-base-bf16

Z-Image checkpoint on the network volume. zimage-base-bf16 = Z-Image 6B base (UNETLoader, CFG and negative prompt). cyberrealistic-zimage-turbo-v8-bf16 = CyberRealistic Z-Image Turbo v8.0 bf16 (UNETLoader with the shared Qwen3 4B encoder and Flux ae). zimage-turbo-bf16-aio = Z-Image-Turbo BF16 all-in-one (CheckpointLoaderSimple; encoder and VAE come from the same file). The two Turbo checkpoints run the distilled schedule automatically: 8 steps at CFG 1 with the negative zeroed, whatever steps and cfg say.

options: zimage-base-bf16cyberrealistic-zimage-turbo-v8-bf16zimage-turbo-bf16-aio

stepsintegerdefault 25min 8max 60

Sampling steps for the base checkpoint (25 is the upstream base template's value; its note suggests 30-50). Not used by a Turbo checkpoint, which always runs 8.

cfgfloatdefault 4.0min 1.0max 10.0

Classifier-free guidance for the base checkpoint (4 is the upstream base template's value; its note suggests 3-5). Not used by a Turbo checkpoint, which always samples at 1.

seedintegerdefault -1

Random seed (-1 = random)

source_imageimagerequired

Source image (PNG/JPEG/WebP). It is scaled so its longest side is 1024 (lanczos) before encoding, which bounds the latent at ~1 MP whatever is uploaded; the output has that size.

denoisefloatdefault 0.6min 0.05max 1.0

Denoise strength: low keeps the source, 1.0 ignores it (the chroma-img2img default of 0.6; no upstream Z-Image image-to-image template sets one). On a Turbo checkpoint the 8-step schedule is shortened the same way.

loraenumdefault none

Optional Z-Image LoRA (A.03.02; see zimage-txt2img). none leaves the graph without a LoRA loader.

options: nonephotoreal-betternudes-v3realistic-snapshot-v5breast-sliderdetail-sliderdetaildaemonz-v1.1

lora_strengthfloatdefault 1.0min -2.0max 2.0

LoRA strength on the model (LoraLoaderModelOnly.strength_model). The sliders are meant to be driven negative as well as positive.

ComfyUI node graph (15)#

The executable ComfyUI prompt graph: 15 nodes across 14 distinct node classes, wired by 8 data dependencies. Nodes tinted green come from a custom node pack this workflow declares; the rest are ComfyUI core / baked-community classes.

flowchart TD n0["1: UNETLoader"] n1["2: CLIPLoader"] n2["3: VAELoader"] n3["4: CheckpointLoaderSimple"] n4["5: LoraLoaderModelOnly"] n5["6: ModelSamplingAuraFlow"] n6["7: CLIPTextEncode"] n7["8: CLIPTextEncode"] n8["9: ConditioningZeroOut"] n9["10: LoadImage"] n10["11: ImageScaleToMaxDimension"] n11["12: VAEEncode"] n12["13: KSampler"] n13["14: VAEDecode"] n14["15: SaveImage"] n6 -->|conditioning| n8 n9 -->|image| n10 n10 -->|pixels| n11 n5 -->|model| n12 n6 -->|positive| n12 n11 -->|latent_image| n12 n12 -->|samples| n13 n13 -->|images| n14

Data-flow DAG — scroll to zoom, drag to pan.

Nodes (15)#

1UNETLoadercore

unet_name = {{checkpoint_map[checkpoint]}} tmplweight_dtype = default

outputs: MODEL

2CLIPLoadercore

clip_name = qwen_3_4b.safetensorstype = lumina2device = default

outputs: CLIP

3VAELoadercore

vae_name = ae.safetensors

outputs: VAE

4CheckpointLoaderSimplecore

ckpt_name = {{checkpoint_map[checkpoint]}} tmpl

outputs: MODELCLIPVAE

5LoraLoaderModelOnlycore

model = {{loader_refs[checkpoint_profile[checkpoint].loader].model}} tmpllora_name = {{lora_map[lora]}} tmplstrength_model = {{lora_strength}} tmpl

outputs: MODEL

6ModelSamplingAuraFlowcore

model = {{lora_ref if lora != 'none' else loader_refs[checkpoint_profile[checkpoint].loader].model}} tmplshift = 3

outputs: MODEL

7CLIPTextEncodecore

text = {{constructed_prompt}} tmplclip = {{loader_refs[checkpoint_profile[checkpoint].loader].clip}} tmpl

outputs: CONDITIONING

8CLIPTextEncodecore

text = {{negative_prompt}} tmplclip = {{loader_refs[checkpoint_profile[checkpoint].loader].clip}} tmpl

outputs: CONDITIONING

9ConditioningZeroOutcore

conditioning = ◂ node 7 · out[0]

outputs: CONDITIONING

10LoadImagecore

image = {{source_image}} tmpl

outputs: IMAGEMASK

11ImageScaleToMaxDimensioncore

image = ◂ node 10 · out[0]upscale_method = lanczoslargest_size = 1024

outputs: IMAGE

12VAEEncodecore

pixels = ◂ node 11 · out[0]vae = {{loader_refs[checkpoint_profile[checkpoint].loader].vae}} tmpl

outputs: LATENT

13KSamplercore

model = ◂ node 6 · out[0]positive = ◂ node 7 · out[0]negative = {{checkpoint_profile[checkpoint].negative}} tmpllatent_image = ◂ node 12 · out[0]seed = {{seed}} tmplsteps = {{distilled_schedule.steps if checkpoint_profile[checkpoint].distilled else steps}} tmplcfg = {{distilled_schedule.cfg if checkpoint_profile[checkpoint].distilled else cfg}} tmplsampler_name = res_multistepscheduler = simpledenoise = {{denoise}} tmpl

outputs: LATENT

14VAEDecodecore

samples = ◂ node 13 · out[0]vae = {{loader_refs[checkpoint_profile[checkpoint].loader].vae}} tmpl

outputs: IMAGE

15SaveImagecore

images = ◂ node 14 · out[0]filename_prefix = isis/zimage-img2img

Prompt construction#

template

{base_prompt}

Variables (1)#

base_prompt

{{prompt}} tmpl

Parameter banks (8)#

The prompt / configuration lookup tables this workflow keys into from its inputs — the vocabulary that turns a style / palette / preset selection into graph parameters.

`option_policy` (2)#

checkpoint

{"zimage-base-bf16": {"distribution": "service", "content": "neutral"}, "cyberrealistic-zimage-turbo-v8-bf16": {"distribution": "service", "content": "racy"}, "zimage-turbo-bf16-aio": {"distribution": "service", "content": "neutral"}}

lora

{"photoreal-betternudes-v3": {"distribution": "service", "content": "explicit"}, "realistic-snapshot-v5": {"distribution": "service", "content": "neutral"}, "breast-slider": {"distribution": "service", "content": "racy"}, "detail-slider": {"distribution": "service", "content": "neutral"}, "detaildaemonz-v1.1": {"distribution": "service", "content": "neutral"}}

`checkpoint_map` (3)#

zimage-base-bf16

z_image_bf16.safetensors

cyberrealistic-zimage-turbo-v8-bf16

cyberrealistic_zimage_turbo_v8_bf16.safetensors

zimage-turbo-bf16-aio

zimage_turbo_bf16_aio.safetensors

`checkpoint_profile` (3)#

zimage-base-bf16

{"loader": "unet", "distilled": false, "negative": ["8", 0]}

cyberrealistic-zimage-turbo-v8-bf16

{"loader": "unet", "distilled": true, "negative": ["9", 0]}

zimage-turbo-bf16-aio

{"loader": "aio", "distilled": true, "negative": ["9", 0]}

`distilled_schedule` (2)#

steps

8

cfg

1.0

`loader_refs` (2)#

unet

{"model": ["1", 0], "clip": ["2", 0], "vae": ["3", 0]}

aio

{"model": ["4", 0], "clip": ["4", 1], "vae": ["4", 2]}

`lora_ref` (2)#

50

`lora_map` (6)#

none

photoreal-betternudes-v3

zimage-photoreal-betternudes-v3.safetensors

realistic-snapshot-v5

zimage-realistic-snapshot-v5.safetensors

breast-slider

zimage-breast-slider.safetensors

detail-slider

zimage-detail-slider.safetensors

detaildaemonz-v1.1

zimage-detaildaemonz-v1.1.safetensors

`requires_families` (3)#

zimagezimage-cyberrealisticzimage-aio

Models & dependencies#

Models required (10)#

z_image_bf16.safetensors

cyberrealistic_zimage_turbo_v8_bf16.safetensors

zimage_turbo_bf16_aio.safetensors

qwen_3_4b.safetensors

ae.safetensors

zimage-photoreal-betternudes-v3.safetensors

zimage-realistic-snapshot-v5.safetensors

zimage-breast-slider.safetensors

zimage-detail-slider.safetensors

zimage-detaildaemonz-v1.1.safetensors

Output contract#

What a successful run of this workflow returns.

type

image

format

png

Taxonomy & routing#

How the control plane classifies this workflow — from the committed workflow-taxonomy-registry.json. It drives the consistency / control surface the agentic director can exercise over the workflow.

assetFamily

portrait-hero-image-bundle

outputPackageProfile

image-single-profile

controlModalities

model-locksampler-scheduler-lockseed-locklatent-reuse

consistencyDimensions

identitylightingenvironment

notes

Z-Image image-to-image at a chosen denoise; a Turbo checkpoint selects the 8-step schedule.

Inputs (10)#

ComfyUI node graph (15)#

Nodes (15)#

Prompt construction#

Variables (1)#

Parameter banks (8)#

option_policy (2)#

checkpoint_map (3)#

checkpoint_profile (3)#

distilled_schedule (2)#

loader_refs (2)#

lora_ref (2)#

lora_map (6)#

requires_families (3)#

Models & dependencies#

Models required (10)#

Output contract#

Taxonomy & routing#

`option_policy` (2)#

`checkpoint_map` (3)#

`checkpoint_profile` (3)#

`distilled_schedule` (2)#

`loader_refs` (2)#

`lora_ref` (2)#

`lora_map` (6)#

`requires_families` (3)#