(This is not an exhaustive changelog)
Profil d'exécution
Description de la source
ComfyUI Workflow for Flux.2 Klein
Any feedback would be appreciated.
📂 Required Models
Diffusion Model: flux2-klein-4b or any of the other versions .../ComfyUI/models/diffusion_models/
https://huggingface.co/Comfy-Org/flux2-klein-4B/tree/main/split_files/diffusion_models GGUF Variants:
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.
Flux.2 Klein Image Edit Workflow — V2.0 is a ComfyUI workflow for editing a loaded image with Flux.2 Klein 4B; it takes an image, text conditioning, a seed, and random noise, and can save an edited or upscaled image.
The workflow encodes and decodes images through VAE stages, samples with noise and seed controls, and includes comparison, upscaling, and saving stages.
V2.0 includes an upscaler path using ImageUpscaleWithModel and UpscaleModelLoader.
Named stages include LoadImage, CLIPTextEncode, RandomNoise, Seed (rgthree), and ReferenceLatent for image, text, noise, seed, and reference-latent handling.
The workflow includes VAEDecode, ImageUpscaleWithModel, Image Comparer (rgthree), and SaveImage for decoding, upscaling, comparison, and saving.
Install the listed custom nodes: ComfyUI-Manager, rgthree-comfy, and ComfyUI-GGUF.
To prepare it, place the diffusion model in .../ComfyUI/models/diffusion_models/, the text encoder in .../ComfyUI/models/text_encoders/, and the VAE in .../ComfyUI/models/vae/.
Suggestion · non vérifié
The workflow lists these model files: 4x_foolhardy_Remacri.pth, flux-2-klein-4b-BF16.gguf, flux-2-klein-4b-fp8.safetensors, flux2-vae.safetensors, and qwen_3_4b.safetensors.
It lists these node packs: rgthree-comfy and comfyui-gguf.
For the distilled setup, use 4 steps, CFG 1.0, and the Euler sampler.
Suggestion · non vérifié
The setup lists flux2-klein-4b or other diffusion-model versions, qwen_3__4b or qwen_3__8b as text encoders, and flux2-vae as the VAE.
Before setup, verify that flux2-vae.safetensors is the intended file for the Flux.2 Klein 4B VAE folder named in the setup.
Suggestion · non vérifié
Before setup, verify the package that provides comfyui-gguf and the exact file for qwen_3_4b.safetensors.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
2 extraitsSource context: 3499 downloads · Type Workflows · Base model Flux.2 Klein 4B
Text Encoder: qwen_3__4b or qwen_3__8b .../ComfyUI/models/text_encoders/
VAE: flux2-vae .../ComfyUI/models/vae/
🧩 Required Custom Nodes
🟩 ComfyUI-Manager (by Comfy-Org ) https://github.com/Comfy-Org/ComfyUI-Manager
🟩 rgthree-comfy (by rgthree ) https://github.com/rgthree/rgthree-comfy
🟩 ComfyUI-GGUF (by city96 ) https://github.com/city96/ComfyUI-GGUF
⚙️ Recommended Settings
Steps: 4 (distilled)
CFG: 1.0 (distilled)
Sampler: Euler
Experiment and enjoy!
Estimation des besoins VRAM
32+ Go estimés
18,9 GB de fichiers de modèle. Total des fichiers du modèle + 25 % de surcharge de chargement + 2 Go de tampon d'exécution, arrondi à l'unité supérieure.
Exigences
Exigences 7Upscaler · 63.9 MB · PTH · Hugging Face · FacehugmanIII/4x_foolhardy_Remacri
Checkpoint · 7.22 GB · GGUF · Hugging Face · unsloth/FLUX.2-klein-4B-GGUF
Checkpoint · 3.79 GB · SAFETENSORS · fp8 · Hugging Face · black-forest-labs/FLUX.2-klein-4b-fp8
VAE · 321 MB · Hugging Face · Comfy-Org/flux2-dev
Text encoder · 7.49 GB · Hugging Face · Comfy-Org/z_image_turbo
Sources possibles
comfyui-gguf
PossiblePack de nœud · Registry
Pack de nœud · Registry
Source context: 3295 downloads · Type Workflows · Base model Flux.2 Klein 4B