Comfy-agent curated_wan_2_2_t2i_14b_gguf_4_step_lora_upscale_insta_portrait

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 "$T/skills/workflows/video_t2v_i2v_avatar/curated_wan_2_2_t2i_14b_gguf_4_step_lora_upscale_insta_portrait" ~/.claude/skills/steliosot-comfy-agent-curated-wan-2-2-t2i-14b-gguf-4-step-lora-upscale-insta-por && rm -rf "$T"

manifest: skills/workflows/video_t2v_i2v_avatar/curated_wan_2_2_t2i_14b_gguf_4_step_lora_upscale_insta_portrait/SKILL.md

source content

curated_wan_2_2_t2i_14b_gguf_4_step_lora_upscale_insta_portrait

Curated workflow skill generated from

Wan 2.2 T2I 14b GGUF + 4 Step Lora + Upscale Insta Portrait.json

Capability Family

```
video_t2v_i2v_avatar
```

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

Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf

models/diffusion_models

```
vae
```
:
```
wan_2.1_vae.safetensors
```
->
```
models/vae
```

clip

umt5_xxl_fp8_e4m3fn_scaled.safetensors

models/clip

Custom Node Requirements

```
ComfyUI-GGUF
```
```
comfyui-kjnodes
```
```
rgthree-comfy
```

Links Extracted From Workflow Notes

Source

Original:

comfy-data/workflows/Wan 2.2 T2I 14b GGUF + 4 Step Lora + Upscale Insta Portrait.json

Routing Metadata

Family:
```
video_t2v_i2v_avatar
```
Input modalities:
```
text_prompt
```
Output modalities:
```
image/png
```
Model families:
```
sd3, wan
```
Node count:
```
15
```
Complexity score:
```
10
```
Resource profile:
```
very_high
```

Estimated runtime:

heavy (can exceed 6 min; best on high-VRAM GPU)

Max latent resolution hint:
```
1088
```
x
```
1360
```
Max sampler steps hint:
```
8
```

Detected Models

diffusion_model

Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf

models/diffusion_models

```
vae
```
:
```
wan_2.1_vae.safetensors
```
->
```
models/vae
```

clip

umt5_xxl_fp8_e4m3fn_scaled.safetensors

models/clip

Detected Custom Nodes

```
ComfyUI-GGUF
```
```
comfyui-kjnodes
```
```
rgthree-comfy
```

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.
Video workflow: usually slower and VRAM-intensive than still-image workflows.