Curated Ep28 Liveportrait Expression Editor With Flux Upscale

Model Requirements

• clip: t5-v1_1-xxl-encoder-Q8_0.gguf -> models/clip
• diffusion_model: flux1-dev-Q8_0.gguf -> models/diffusion_models
• vae: ae.safetensors -> models/vae
• upscale_model: 4x_NMKD-Siax_200k.pth -> models/upscale_models

Custom Node Requirements

• None detected.

Links Extracted From Workflow Notes

• None detected.

Source

• Original: comfy-data/workflows/Ep28 LivePortrait Expression Editor with Flux Upscale.json

Routing Metadata

• Family: video_t2v_i2v_avatar
• Input modalities: image, text_prompt
• Output modalities: image/png
• Model families: flux
• Node count: 27
• Complexity score: 7
• Resource profile: high
• Estimated runtime: slow (often 2-6 min depending on model/server load)
• Max latent resolution hint: NonexNone
• Max sampler steps hint: 20

Detected Models

• clip: t5-v1_1-xxl-encoder-Q8_0.gguf -> models/clip
• diffusion_model: flux1-dev-Q8_0.gguf -> models/diffusion_models
• vae: ae.safetensors -> models/vae
• upscale_model: 4x_NMKD-Siax_200k.pth -> models/upscale_models

Detected Custom Nodes

• None detected.

Runtime Warnings

• Large model(s) detected; ensure enough VRAM and disk space.
• Video workflow: usually slower and VRAM-intensive than still-image workflows.