Generated reference · ComfyUI workflow · chroma

Chroma Inpaint

Repaint the white region of a mask image with a Chroma checkpoint; untouched pixels are composited back from the source.

chroma16nodesGPU A5000out image~40sv1.0.0
workflow.json
On this page
16Graph nodes
14Node classes
10Inputs
6Models

Tags: chromarunpod-serverlessvolume-backedinpaint

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 a tiger's eye, intricately detailed fur, natural lighting, sharp focus, highest quality
Positive prompt in natural prose (Chroma responds to descriptive photography language)
negative_promptstringdefault This greyscale unfinished sketch has bad proportions, is featureless and disfigured. It is a blurry ugly mess with excessive gaussian blur, riddled with watermarks and signatures, smudged with leaking colors and nonsensical orientation of objects. Messy and abstract, filled with artifacts that disrupt the coherency of the composition, extreme chromatic aberrations and inconsistent lighting. Dull, monochrome colors and countless artistic errors.
Negative prompt (Chroma is CFG-guided, so this is honoured)
checkpointenumdefault chroma1-hd
Full-precision Chroma checkpoint on the network volume. ungloryhail-bf16 = UnGloryHail BF16 (A.03.01, Civitai model-version 2898818, the BF16 file 2776781 rather than the version's fp8 primary; content explicit; not rendered on a GPU yet, A.03.01 live still owed).
options: chroma1-hduncanny-v13-bf16photonic-fusion-debloated-bf16ungloryhail-bf16
stepsintegerdefault 26min 8max 60
Sampling steps (26 is the Chroma1-HD reference)
cfgfloatdefault 3.8min 1.0max 10.0
Classifier-free guidance (3.8 is the Chroma1-HD reference)
seedintegerdefault -1
Random seed (-1 = random)
source_imageimagerequired
Source image
mask_imageimagerequired
Black/white mask image, white = repaint
grow_mask_byintegerdefault 8min 0max 64
Dilate the mask by this many pixels before inpainting
denoisefloatdefault 1.0min 0.2max 1.0
Denoise strength inside the mask

ComfyUI node graph (16)#

The executable ComfyUI prompt graph: 16 nodes across 14 distinct node classes, wired by 19 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: ModelSamplingAuraFlow"] n4["5: T5TokenizerOptions"] n5["6: CLIPTextEncode"] n6["7: CLIPTextEncode"] n7["8: LoadImage"] n8["9: LoadImage"] n9["10: ImageToMask"] n10["11: GrowMask"] n11["12: VAEEncodeForInpaint"] n12["13: KSampler"] n13["14: VAEDecode"] n14["15: ImageCompositeMasked"] n15["16: SaveImage"] n0 -->|model| n3 n1 -->|clip| n4 n4 -->|clip| n5 n4 -->|clip| n6 n8 -->|image| n9 n9 -->|mask| n10 n7 -->|pixels| n11 n2 -->|vae| n11 n10 -->|mask| n11 n3 -->|model| n12 n5 -->|positive| n12 n6 -->|negative| n12 n11 -->|latent_image| n12 n12 -->|samples| n13 n2 -->|vae| n13 n7 -->|destination| n14 n13 -->|source| n14 n10 -->|mask| n14 n14 -->|images| n15
Data-flow DAG — scroll to zoom, drag to pan.

Nodes (16)#

1UNETLoadercore
unet_name = {{checkpoint_map[checkpoint]}} tmplweight_dtype = default
outputs: MODEL
2CLIPLoadercore
clip_name = t5xxl_fp16.safetensorstype = chromadevice = default
outputs: CLIP
3VAELoadercore
vae_name = ae.safetensors
outputs: VAE
4ModelSamplingAuraFlowcore
model = ◂ node 1 · out[0]shift = 1.0
outputs: MODEL
5T5TokenizerOptionscore
clip = ◂ node 2 · out[0]min_padding = 1min_length = 0
outputs: CLIP
6CLIPTextEncodecore
text = {{constructed_prompt}} tmplclip = ◂ node 5 · out[0]
outputs: CONDITIONING
7CLIPTextEncodecore
text = {{negative_prompt}} tmplclip = ◂ node 5 · out[0]
outputs: CONDITIONING
8LoadImagecore
image = {{source_image}} tmpl
outputs: IMAGEMASK
9LoadImagecore
image = {{mask_image}} tmpl
outputs: IMAGEMASK
10ImageToMaskcore
image = ◂ node 9 · out[0]channel = red
outputs: MASK
11GrowMaskcore
mask = ◂ node 10 · out[0]expand = {{grow_mask_by}} tmpltapered_corners = true
outputs: MASK
12VAEEncodeForInpaintcore
pixels = ◂ node 8 · out[0]vae = ◂ node 3 · out[0]mask = ◂ node 11 · out[0]grow_mask_by = 6
outputs: LATENT
13KSamplercore
model = ◂ node 4 · out[0]positive = ◂ node 6 · out[0]negative = ◂ node 7 · out[0]latent_image = ◂ node 12 · out[0]seed = {{seed}} tmplsteps = {{steps}} tmplcfg = {{cfg}} tmplsampler_name = eulerscheduler = betadenoise = {{denoise}} tmpl
outputs: LATENT
14VAEDecodecore
samples = ◂ node 13 · out[0]vae = ◂ node 3 · out[0]
outputs: IMAGE
15ImageCompositeMaskedcore
destination = ◂ node 8 · out[0]source = ◂ node 14 · out[0]x = 0y = 0resize_source = falsemask = ◂ node 11 · out[0]
outputs: IMAGE
16SaveImagecore
images = ◂ node 15 · out[0]filename_prefix = isis/chroma-inpaint

Prompt construction#

template
{base_prompt}

Variables (1)#

base_prompt
{{prompt}} tmpl

Parameter banks (3)#

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 (1)#

checkpoint
{"chroma1-hd": {"distribution": "service", "content": "neutral"}, "uncanny-v13-bf16": {"distribution": "service", "content": "neutral"}, "photonic-fusion-debloated-bf16": {"distribution": "internal_only", "content": "neutral"}, "ungloryhail-bf16": {"distribution": "service", "content": "explicit"}}

checkpoint_map (4)#

chroma1-hd
Chroma1-HD.safetensors
uncanny-v13-bf16
uncannyPhotorealism_v13_bf16.safetensors
photonic-fusion-debloated-bf16
photonicFusionChroma_debloated_bf16.safetensors
ungloryhail-bf16
ungloryhail_bf16.safetensors

requires_families (1)#

chroma-core

Models & dependencies#

Models required (6)#

Chroma1-HD.safetensors
uncannyPhotorealism_v13_bf16.safetensors
photonicFusionChroma_debloated_bf16.safetensors
ungloryhail_bf16.safetensors
t5xxl_fp16.safetensors
ae.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-lockcontrolnet-inpaintlatent-reuse
consistencyDimensions
identitylightingenvironment
notes
Chroma inpaint with a user mask; untouched pixels composited back.