Comfy-agent workflow_flux_txt2img_with_cn_depth_and_upscaler_portrait_instagram_1080x1350px_4_5

install

source · Clone the upstream repo

git clone https://github.com/steliosot/comfy-agent

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/steliosot/comfy-agent "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/workflows/upscaling/workflow_flux_txt2img_with_cn_depth_and_upscaler_portrait_instagram_1080x1350px_4_5" ~/.claude/skills/steliosot-comfy-agent-workflow-flux-txt2img-with-cn-depth-and-upscaler-portrait--cfb149 && rm -rf "$T"

manifest: skills/workflows/upscaling/workflow_flux_txt2img_with_cn_depth_and_upscaler_portrait_instagram_1080x1350px_4_5/SKILL.md

source content

workflow_flux_txt2img_with_cn_depth_and_upscaler_portrait_instagram_1080x1350px_4_5

Imported workflow skill generated from

Flux txt2img with CN Depth and Upscaler - Portrait Instagram 1080x1350px 4-5.json

Family

```
upscaling
```

Inputs

Optional runtime overrides supported by

run(...)

```
prompt
```
```
negative_prompt
```
```
width
```
,
```
height
```
```
seed
```
,
```
steps
```
,
```
cfg
```
```
sampler_name
```
,
```
scheduler
```
,
```
denoise
```
```
server
```
,
```
headers
```
,
```
api_prefix
```

Outputs

Returns JSON with:
- ```
status
```
- ```
prompt_id
```
- ```
output_images
```

Model Requirements

upscale_model

4x_NMKD-Siax_200k.pth

models/upscale_models

clip

t5-v1_1-xxl-encoder-Q8_0.gguf

models/clip

```
vae
```
:
```
ae.safetensors
```
->
```
models/vae
```

controlnet

flux-cn-pro-2.safetensors

models/controlnet

diffusion_model

flux1-dev-Q8_0.gguf

models/diffusion_models

Custom Node Requirements

```
ComfyUI-TiledDiffusion
```
```
comfyui-easy-use
```
```
comfyui-gguf
```
```
comfyui_controlnet_aux
```

Links

Routing Metadata

Family:
```
upscaling
```
Input modalities:
```
image, text_prompt
```
Output modalities:
```
image/png
```
Model families:
```
flux, sd3
```
Node count:
```
36
```
Complexity score:
```
7
```
Resource profile:
```
high
```

Estimated runtime:

slow (often 2-6 min depending on model/server load)

Max latent resolution hint:
```
880
```
x
```
1088
```
Max sampler steps hint:
```
30
```

Detected Models

upscale_model

4x_NMKD-Siax_200k.pth

models/upscale_models

clip

t5-v1_1-xxl-encoder-Q8_0.gguf

models/clip

```
vae
```
:
```
ae.safetensors
```
->
```
models/vae
```

controlnet

flux-cn-pro-2.safetensors

models/controlnet

diffusion_model

flux1-dev-Q8_0.gguf

models/diffusion_models

Detected Custom Nodes

```
ComfyUI-TiledDiffusion
```
```
comfyui-easy-use
```
```
comfyui-gguf
```
```
comfyui_controlnet_aux
```

Runtime Warnings

Large model(s) detected; ensure enough VRAM and disk space.
Medium-high resolution detected; expect moderate extra runtime.
Multiple custom nodes required; verify node installation/version compatibility.