Comfy-agent workflow_ep51_cosmos_predict2_14b_image2image
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 "$T/skills/workflows/txt2img/workflow_ep51_cosmos_predict2_14b_image2image" ~/.claude/skills/steliosot-comfy-agent-workflow-ep51-cosmos-predict2-14b-image2image && rm -rf "$T"
manifest:
skills/workflows/txt2img/workflow_ep51_cosmos_predict2_14b_image2image/SKILL.mdsource content
workflow_ep51_cosmos_predict2_14b_image2image
Imported workflow skill generated from
EP51 Cosmos Predict2 14B Image2Image.json.
Family
txt2img
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
:clip
->oldt5_xxl_fp8_e4m3fn_scaled.safetensorsmodels/clip
:diffusion_model
->cosmos-predict2-14b-t2i-ex3-q8_0.ggufmodels/diffusion_models
:vae
->wan_2.1_vae.safetensorsmodels/vae
Custom Node Requirements
comfyui-easy-usecomfyui-gguf
Links
- https://discord.com/invite/gggpkVgBf3
- https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors
- https://huggingface.co/calcuis/cosmos-predict2-gguf/resolve/main/cosmos-predict2-14b-t2i-ex3-q4_0.gguf?download=true
- https://huggingface.co/calcuis/cosmos-predict2-gguf/resolve/main/cosmos-predict2-14b-t2i-ex3-q8_0.gguf?download=true
- https://huggingface.co/calcuis/cosmos-predict2-gguf/tree/main
- https://huggingface.co/comfyanonymous/cosmos_1.0_text_encoder_and_VAE_ComfyUI/resolve/main/text_encoders/oldt5_xxl_fp8_e4m3fn_scaled.safetensors
- https://www.youtube.com/@pixaroma
Routing Metadata
- Family:
txt2img - Input modalities:
image, text_prompt - Output modalities:
image/png - Model families:
wan - Node count:
12 - Complexity score:
4 - Resource profile:
medium - Estimated runtime:
moderate (about 30-120s depending on server) - Max latent resolution hint:
xNoneNone - Max sampler steps hint:
35
Detected Models
:clip
->oldt5_xxl_fp8_e4m3fn_scaled.safetensorsmodels/clip
:diffusion_model
->cosmos-predict2-14b-t2i-ex3-q8_0.ggufmodels/diffusion_models
:vae
->wan_2.1_vae.safetensorsmodels/vae
Detected Custom Nodes
comfyui-easy-usecomfyui-gguf
Runtime Warnings
- Large model(s) detected; ensure enough VRAM and disk space.
- Uses custom nodes; missing nodes can cause validation/runtime failures.