Workflow Ep51 Cosmos Predict2 2b Text2image

workflow_ep51_cosmos_predict2_2b_text2image

Imported workflow skill generated from EP51 Cosmos Predict2 2B Text2Image.json.

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

Model Requirements

• vae: wan_2.1_vae.safetensors -> models/vae
• clip: oldt5_xxl_fp8_e4m3fn_scaled.safetensors -> models/clip
• diffusion_model: cosmos_predict2_2B_t2i.safetensors -> models/diffusion_models

Custom Node Requirements

• None detected.

Links

• https://discord.com/invite/gggpkVgBf3
• https://huggingface.co/Comfy-Org/Cosmos_Predict2_repackaged/resolve/main/cosmos_predict2_2B_t2i.safetensors?download=true
• https://huggingface.co/Comfy-Org/Cosmos_Predict2_repackaged/tree/main
• https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors
• 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: text_prompt
• Output modalities: image/png
• Model families: sd3, wan
• Node count: 10
• Complexity score: 4
• Resource profile: medium
• Estimated runtime: moderate (about 30-120s depending on server)
• Max latent resolution hint: 1024x1024
• Max sampler steps hint: 35

Detected Models

• vae: wan_2.1_vae.safetensors -> models/vae
• clip: oldt5_xxl_fp8_e4m3fn_scaled.safetensors -> models/clip
• diffusion_model: cosmos_predict2_2B_t2i.safetensors -> models/diffusion_models

Detected Custom Nodes

• None detected.

Runtime Warnings

• Large model(s) detected; ensure enough VRAM and disk space.
• Medium-high resolution detected; expect moderate extra runtime.