Reference Pose Lora Workflow. Low VRAM GGUF. — v1.0
This is my implementation of Reference Pose workflow, designed for weak GPUs.
Profil d'exécution
- Accès
- Flux de travail externe
- Statut
- Présenté
- Version
- workflow_flux_kontext_pose_reference_control.json
- Source
- Civitai
- Mis à jour
- 3 nov. 2026
Description de la source
No release description captured.
Exigences
Modèles
7- Fichier indiqué
VAE · 878 MB · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged
clip_l.safetensors
PossibleText encoder · Unknown
Checkpoint · 129 MB · PT · Unknown
Diffusion model · 7.71 GB · GGUF · Unknown
LoRA · 328 MB · SAFETENSORS · Unknown
Text encoder · 4.80 GB · SAFETENSORS · FP16 + FP32 + FP8 (tensor header) · Unknown
yolox_l.onnx
Non résoluCheckpoint · Unknown
Packs de nœuds
5comfyui_controlnet_aux
PossiblePack de nœud · Registry
comfyui-custom-scripts
TrouvéPack de nœud · Registry
ComfyUI-GGUF
PossiblePack de nœud · Registry
rgthree-comfy
TrouvéPack de nœud · Registry
teacache
PossiblePack de nœud · Registry
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
Objectif
Use this Flux.1 Kontext Reference Pose workflow to generate images guided by a pose-reference image, with preview and save outputs; its graph includes LoadImage, DWPreprocessor, and ReferenceLatent nodes.
Suggestion · non vérifié
Flux
The graph also includes text-encoding, FluxGuidance, KSampler, TeaCache, and VAE encode/decode nodes.
Entrées et sorties
The graph includes LoadImage and CLIPTextEncode nodes for image and text inputs, plus PreviewImage and SaveImage nodes for image outputs.
Installation
The author reports testing with an RTX 3060 12GB GPU and 16 GB DDR4 RAM.
Setup notes provide links for the Flux GGUF, CLIP encoder files, VAE, and refcontrol_pose.safetensors LoRA.
Dépendances
The workflow file lists these model files: ae.safetensors, clip_l.safetensors, dw-ll_ucoco_384_bs5.torchscript.pt, flux1-kontext-dev-Q5_K_S.gguf, refcontrol_pose.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors, and yolox_l.onnx.
Listed node packs and versions are comfyui_controlnet_aux (1.1.0), comfyui-custom-scripts (1.2.5), ComfyUI-GGUF (b3ec875a68d94b758914fd48d30571d953bb7a54), rgthree-comfy (1.0.2506230015), and teacache (1.9.0).
Configuration
The title labels this version “Low VRAM GGUF”; the listed base model is Flux.1 Kontext.
Précautions
The file list gives no download links for dw-ll_ucoco_384_bs5.torchscript.pt or yolox_l.onnx; confirm where to get them before setup.
Suggestion
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 source
Sources
1 sourceWorkflow instructions
Author notes from workflow_flux_kontext_pose_reference_control.json · selected release
flux guff model: https://huggingface.co/QuantStack/FLUX.1-Kontext-dev-GGUF/tree/main clip1: https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors clip2: https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/t5xxl_fp8_e4m3fn_scaled.safetensors vae: https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/blob/main/split_files/vae/ae.safetensors lora: https://civitai.com/models/1894154/refcontrol-flux-kontext-reference-pose-lora
Download files
Artefacts du modèle
2 artefacts
Artefacts du modèle
2 artefactsworkflow_flux_kontext_pose_reference_control.json
json · 26,4 KB · SHA-256 d1c71369c86d…7ea3
Download fileExtraits de sources
3 extraits
Extraits de sources
3 extraitsSource context: 517 downloads · Type Workflows · Base model Flux.1 Kontext
Source context: 496 downloads · Type Workflows · Base model Flux.1 Kontext
Source context: 424 downloads · Type Workflows · Base model Flux.1 Kontext
