Workflow Ep53 Flux 1 Kontext Dev Nunchaku Transform To Mandala

workflow_ep53_flux_1_kontext_dev_nunchaku_transform_to_mandala

Imported workflow skill generated from EP53 Flux 1 Kontext Dev (Nunchaku) - Transform to Mandala.json.

Family

• upscaling

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

• upscale_model: 4x_NMKD-Siax_200k.pth -> models/upscale_models
• vae: ae.safetensors -> models/vae

Custom Node Requirements

• ComfyUI-nunchaku
• comfyui-easy-use

Links

• https://bfl.ai/models/flux-kontext
• https://discord.com/invite/gggpkVgBf3
• https://docs.comfy.org/tutorials/flux/flux-1-kontext-dev
• https://docs.comfy.org/tutorials/flux/flux-1-kontext-dev#flux-kontext-prompt-techniques
• https://github.com/Tavris1/ComfyUI-Easy-Install/tree/Windows-Nunchaku
• https://github.com/mit-han-lab/ComfyUI-nunchaku
• https://huggingface.co/Akumetsu971/SD_Anime_Futuristic_Armor/resolve/main/4x_NMKD-Siax_200k.pth?download=true
• https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/resolve/main/split_files/vae/ae.safetensors?download=true
• https://huggingface.co/Pixaroma/flux-kontext-loras/resolve/main/transform_to_mandala.safetensors?download=true
• https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors?download=true
• https://huggingface.co/mit-han-lab/nunchaku-flux.1-kontext-dev/resolve/main/svdq-int4_r32-flux.1-kontext-dev.safetensors?download=true
• https://huggingface.co/mit-han-lab/nunchaku-flux.1-kontext-dev/tree/main
• https://huggingface.co/mit-han-lab/nunchaku-t5/resolve/main/awq-int4-flux.1-t5xxl.safetensors?download=true
• https://www.youtube.com/@pixaroma

Routing Metadata

• Family: upscaling
• Input modalities: image, text_prompt
• Output modalities: image/png
• Model families: flux
• Node count: 33
• Complexity score: 1
• Resource profile: low
• Estimated runtime: fast (usually under 30s on modern GPU)
• Max latent resolution hint: NonexNone
• Max sampler steps hint: 20

Detected Models

• upscale_model: 4x_NMKD-Siax_200k.pth -> models/upscale_models
• vae: ae.safetensors -> models/vae

Detected Custom Nodes

• ComfyUI-nunchaku
• comfyui-easy-use

Runtime Warnings

• Uses custom nodes; missing nodes can cause validation/runtime failures.