Comfy-agent workflow_wan_2_2_rapid_mega_aio_text_to_video
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 "$T/skills/workflows/video_t2v_i2v_avatar/workflow_wan_2_2_rapid_mega_aio_text_to_video" ~/.claude/skills/steliosot-comfy-agent-workflow-wan-2-2-rapid-mega-aio-text-to-video && rm -rf "$T"
manifest:
skills/workflows/video_t2v_i2v_avatar/workflow_wan_2_2_rapid_mega_aio_text_to_video/SKILL.mdsource content
workflow_wan_2_2_rapid_mega_aio_text_to_video
Imported workflow skill generated from
Wan 2.2 Rapid Mega AIO Text to Video.json.
Family
video_t2v_i2v_avatar
Inputs
- Optional runtime overrides supported by
:run(...)promptnegative_prompt
,widthheight
,seed
,stepscfg
,sampler_name
,schedulerdenoise
,server
,headersapi_prefix
Outputs
- Returns JSON with:
statusprompt_idoutput_images
Model Requirements
:checkpoint
->wan2.2-rapid-mega-aio-v8.safetensorsmodels/checkpoints
Custom Node Requirements
comfyui-videohelpersuite
Links
- https://discord.com/invite/gggpkVgBf3
- https://huggingface.co/Phr00t/WAN2.2-14B-Rapid-AllInOne/resolve/main/Mega-v8/wan2.2-rapid-mega-aio-v8.safetensors?download=true
- https://huggingface.co/Phr00t/WAN2.2-14B-Rapid-AllInOne/tree/main
- https://huggingface.co/Phr00t/WAN2.2-14B-Rapid-AllInOne/tree/main/Mega-v8
- https://www.youtube.com/@pixaroma
Routing Metadata
- Family:
video_t2v_i2v_avatar - Input modalities:
text_prompt - Output modalities:
video/mp4 - Model families:
sd3, wan - Node count:
13 - Complexity score:
5 - Resource profile:
medium - Estimated runtime:
moderate (about 30-120s depending on server) - Max latent resolution hint:
xNoneNone - Max sampler steps hint:
4
Detected Models
:checkpoint
->wan2.2-rapid-mega-aio-v8.safetensorsmodels/checkpoints
Detected Custom Nodes
comfyui-videohelpersuite
Runtime Warnings
- Uses custom nodes; missing nodes can cause validation/runtime failures.
- Video workflow: usually slower and VRAM-intensive than still-image workflows.