---

name: curated_ep28_liveportrait_expression_editor_with_flux_upscale description: > Curated ComfyUI workflow imported from Ep28 LivePortrait Expression Editor with Flux Upscale.json. homepage: https://github.com/steliosot/comfy-agent metadata.clawdbot.os: ["darwin", "linux"] metadata.clawdbot.requires.bins: ["python3"] metadata.clawdbot.requires.env: ["COMFY_URL", "COMFY_AUTH_HEADER"] metadata.clawdbot.files: ["workflow.json", "skill.py", "skill.yaml", "scripts/*"] metadata.clawdbot.tags: ["comfyui", "workflow", "curated", "video_t2v_i2v_avatar"] metadata.clawdbot.category: "media-generation" metadata.clawdbot.input_type: "image/png" metadata.clawdbot.output_type: "image/png" metadata.clawdbot.output_can_feed_into: [] metadata.clawdbot.accepts_input_from: [] metadata.clawdbot.priority: 70

curated_ep28_liveportrait_expression_editor_with_flux_upscale

Curated workflow skill generated from Ep28 LivePortrait Expression Editor with Flux Upscale.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

• 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.