FLUX 3 Image Klein ComfyUI Workflows (the four official templates)
==================================================================

Article: https://freakyjolly.com/flux-3-image-klein-comfyui/

What's inside:
  - image_flux3_klein_distilled_t2i.json: ComfyUI workflow (UI format). Drag it onto the ComfyUI canvas or use Workflow > Open.
  - image_flux3_klein_distilled_image_edit.json: ComfyUI workflow (UI format). Drag it onto the ComfyUI canvas or use Workflow > Open.
  - image_flux3_klein_t2i.json: ComfyUI workflow (UI format). Drag it onto the ComfyUI canvas or use Workflow > Open.
  - image_flux3_klein_image_edit.json: ComfyUI workflow (UI format). Drag it onto the ComfyUI canvas or use Workflow > Open.

Required models (download each file and put it in the folder shown):
  - flux2-vae.safetensors
      folder: ComfyUI/models/vae/
      download: https://huggingface.co/Comfy-Org/Fibo-2.0/resolve/main/vae/flux2-vae.safetensors
  - flux3-image-klein-base-int8-convrot.safetensors
      folder: ComfyUI/models/diffusion_models/
      download: https://huggingface.co/black-forest-labs/flux-3-image-klein-comfy/resolve/main/diffusion_models/flux3-image-klein-base-int8-convrot.safetensors
  - flux3-image-klein-int8-convrot.safetensors
      folder: ComfyUI/models/diffusion_models/
      download: https://huggingface.co/black-forest-labs/flux-3-image-klein-comfy/resolve/main/diffusion_models/flux3-image-klein-int8-convrot.safetensors
  - qwen3.5_9b_flux3_prompt_upsampler_w4a8.safetensors
      folder: ComfyUI/models/text_encoders/
      download: https://huggingface.co/black-forest-labs/flux-3-image-klein-comfy/resolve/main/text_encoders/qwen3.5_9b_flux3_prompt_upsampler_w4a8.safetensors
  - qwen3vl_4b_int8_convrot.safetensors
      folder: ComfyUI/models/text_encoders/
      download: https://huggingface.co/Comfy-Org/Fibo-2.0/resolve/main/text_encoders/qwen3vl_4b_int8_convrot.safetensors

Custom nodes:
  - None. Every node is part of ComfyUI core (update ComfyUI to the latest version).

How to use:
  1. Update ComfyUI past the last release tag and restart.
  2. Accept the gated terms on https://huggingface.co/black-forest-labs/flux-3-image-klein, then download the files listed into the folders shown.
  3. Drag image_flux3_klein_distilled_t2i.json (start here) onto the canvas, or one of the edit / base templates.
  4. Type your prompt and queue (distilled: 16 steps, base: 50 steps, guidance 3.5).

Notes:
  - Distilled = everyday text-to-image and edits. Base = for LoRAs trained on the base model and 50-step comparisons.
  - Model filenames are the ones saved in the official templates (INT8 builds by default).

Credits and licence:
  - These are the official Comfy-Org workflow templates (comfyui-workflow-templates, MIT licence), included unchanged.
  - FLUX 3 Image Klein weights: FLUX Kommunity License.

Model weights are not included. Each model keeps its own licence; check the model page before commercial use.
Workflow shared by FreakyJolly.com.
