---

name: curated_ep45_flux_dev_q8_gguf_with_controlnet_dw_pose_lora description: > Curated ComfyUI workflow imported from Ep45 Flux Dev Q8 GGUF with ControlNet DW Pose + Lora.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", "txt2img"] 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_ep45_flux_dev_q8_gguf_with_controlnet_dw_pose_lora

Curated workflow skill generated from Ep45 Flux Dev Q8 GGUF with ControlNet DW Pose + Lora.json.

Capability 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 (includes image/video entries reported by Comfy history)

Model Requirements

• vae: ae.safetensors -> models/vae
• controlnet: flux-cn-pro-2.safetensors -> models/controlnet
• clip: t5-v1_1-xxl-encoder-Q8_0.gguf -> models/clip
• diffusion_model: flux1-dev-Q8_0.gguf -> models/diffusion_models

Custom Node Requirements

• comfyui-gguf
• comfyui_controlnet_aux
• kaytool
• rgthree-comfy

Links Extracted From Workflow Notes

• https://civitai.com/api/download/models/895148?type=Model&format=SafeTensor
• https://discord.com/invite/gggpkVgBf3
• https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0
• https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0/resolve/main/diffusion_pytorch_model.safetensors?download=true
• https://huggingface.co/black-forest-labs/FLUX.1-schnell
• https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors?download=true
• https://huggingface.co/city96/FLUX.1-dev-gguf/resolve/main/flux1-dev-Q8_0.gguf?download=true
• https://huggingface.co/city96/FLUX.1-dev-gguf/tree/main
• https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/resolve/main/t5-v1_1-xxl-encoder-Q8_0.gguf?download=true
• https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main
• https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors?download=true
• https://www.youtube.com/@pixaroma

Source

• Original: comfy-data/workflows/Ep45 Flux Dev Q8 GGUF with ControlNet DW Pose + Lora.json

Routing Metadata

• Family: txt2img
• Input modalities: image, text_prompt
• Output modalities: image/png
• Model families: flux, sd3
• Node count: 21
• Complexity score: 7
• Resource profile: high
• Estimated runtime: slow (often 2-6 min depending on model/server load)
• Max latent resolution hint: 1024x1024
• Max sampler steps hint: 30

Detected Models

• vae: ae.safetensors -> models/vae
• controlnet: flux-cn-pro-2.safetensors -> models/controlnet
• clip: t5-v1_1-xxl-encoder-Q8_0.gguf -> models/clip
• diffusion_model: flux1-dev-Q8_0.gguf -> models/diffusion_models

Detected Custom Nodes

• comfyui-gguf
• comfyui_controlnet_aux
• kaytool
• rgthree-comfy

Runtime Warnings

• Large model(s) detected; ensure enough VRAM and disk space.
• Medium-high resolution detected; expect moderate extra runtime.
• Multiple custom nodes required; verify node installation/version compatibility.