Pose Selector Flux Kontext Workflow

Pose Selector Flux Kontext Workflow, based on Flux.1 Kontext, is for choosing a pose for a character and producing an output image. It can use a DW Pose image and a character image, a built-in pose choice and a Reference Image, or a built-in pose image and a full-body character—何

It includes three variants: 1_recomended_pose_lora, classic_pose_lora, and classic_without_pose_lora.

1_recomended_pose_lora uses a DW Pose image from the poses folder and a character image. classic_pose_lora uses a built-in pose list and a Reference Image. classic_without_pose_lora uses predefined prompts and pose images baked into the workflow, without a LoRA.

For classic_without_pose_lora, choose a pose from the list and load a full-body character image; the output image uses the size you choose.

To run classic_without_pose_lora, choose a pose in the “Choose your pose” node, load a full-body character image, and click run.

The listed model files are ae.safetensors, clip_l.safetensors, flux1-kontext-dev-Q5_K_S.gguf, FluxKontext/refcontrol_pose.safetensors, and t5xxl_fp8_e4m3fn_scaled.safetensors.

The listed node packs are comfyui-custom-scripts, ComfyUI-GGUF, rgthree-comfy, and teacache.

Keep the reference-image height above 1080px as recommended; changing it can make pose following better or worse.

To add a pose or output image size, duplicate an existing group whose title contains “pos” or “size”; new poses or sizes appear in the “Choose your” list.

No license is specified for this workflow; check its source page before use.

Vorschlag · nicht geprüft

Before running, verify that your setup has the listed model files and node packs.

Vorschlag · nicht geprüft