Comfy-agent curated_ep45_flux_dev_q8_gguf_with_controlnet_depth_dw_pose

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 "$T/skills/workflows/txt2img/curated_ep45_flux_dev_q8_gguf_with_controlnet_depth_dw_pose" ~/.claude/skills/steliosot-comfy-agent-curated-ep45-flux-dev-q8-gguf-with-controlnet-depth-dw-pos && rm -rf "$T"

manifest: skills/workflows/txt2img/curated_ep45_flux_dev_q8_gguf_with_controlnet_depth_dw_pose/SKILL.md

source content

curated_ep45_flux_dev_q8_gguf_with_controlnet_depth_dw_pose

Curated workflow skill generated from

Ep45 Flux Dev Q8 GGUF with ControlNet Depth + DW Pose.json

Capability Family

```
txt2img
```

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
```
  (includes image/video entries reported by Comfy history)

Model Requirements

diffusion_model

flux1-dev-Q8_0.gguf

models/diffusion_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

Custom Node Requirements

```
comfyui-gguf
```
```
comfyui_controlnet_aux
```
```
kaytool
```

Links Extracted From Workflow Notes

Source

Original:

comfy-data/workflows/Ep45 Flux Dev Q8 GGUF with ControlNet Depth + DW Pose.json

Routing Metadata

Family:
```
txt2img
```
Input modalities:
```
image, text_prompt
```
Output modalities:
```
image/png
```
Model families:
```
flux, sd3
```
Node count:
```
22
```
Complexity score:
```
6
```
Resource profile:
```
high
```

Estimated runtime:

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

Max latent resolution hint:
```
1024
```
x
```
1024
```
Max sampler steps hint:
```
30
```

Detected Models

diffusion_model

flux1-dev-Q8_0.gguf

models/diffusion_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

Detected Custom Nodes

```
comfyui-gguf
```
```
comfyui_controlnet_aux
```
```
kaytool
```

Runtime Warnings

Large model(s) detected; ensure enough VRAM and disk space.
Medium-high resolution detected; expect moderate extra runtime.
Uses custom nodes; missing nodes can cause validation/runtime failures.