SIMPLE FLUX GGUF IMG2IMG WORKFLOW by weshouldhaveshotguns
Laufzeitprofil
Quellenbeschreibung
SIMPLE FLUX GGUF IMG2IMG WORKFLOW by weshouldhaveshotguns
This workflow builds on the SIMPLE FLUX GGUF setup, tailored for img2img in ComfyUI. It’s all about keeping things simple, accessible, and optimized, using GGUF-quantized models for low-VRAM GPUs.
Key Features:
Easy Setup : Includes links to all required and optional files, so you’re ready to go without any hassle.
Img2Img Settings Rundown : Get a quick breakdown of key settings used for img2img transformations.
Prompting Tips : Handy best practices for img2img prompts, helping you tweak transformations without losing control of the original image.
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This ComfyUI workflow is for transforming an existing image with prompt text using Flux GGUF img2img and saving the resulting image.
The included notes explain img2img settings and prompting tips for adjusting transformations while keeping control of the original image.
LoadImage, CLIPTextEncode, and SaveImage are named nodes for working with the source image, prompt text, and saved output.
The workflow is tailored for ComfyUI and GGUF-quantized models for low-VRAM GPUs; Flux.1 D is listed as the base model.
The setup notes include links to required and optional files.
The listed model files are ae.safetensors, clip_l.safetensors, flux1-dev-Q8_0.gguf, and t5-v1_1-xxl-encoder-Q8_0 (1).gguf.
Named nodes include BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoaderGGUF, FluxGuidance, ImageScaleToTotalPixels, KSamplerSelect, and LoadImage.
Other named nodes include Power Lora Loader (rgthree), RandomNoise, SamplerCustomAdvanced, SaveImage, UnetLoaderGGUF, VAEDecode, VAEEncode, and VAELoader.
Use the included img2img settings rundown and prompting tips when adjusting transformations.
Vorschlag · nicht geprüft
Before using the workflow, verify that the listed model files and node names are available in your ComfyUI setup.
Vorschlag · nicht geprüft
No license is specified in the available workflow details.
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
2 AuszügeSource context: 860 downloads · Type Workflows · Base model Flux.1 D
Built to be intuitive, this workflow is ideal for both newcomers and seasoned users looking to explore img2img in Flux. Dive in, experiment, and get the most out of your images!
Remaining hardware or download-size estimates are not available yet.
Anforderungen
VAE · Civitai · 1223425
Text encoder · 235 MB · SAFETENSORS · Hugging Face · diamkan/comfyui_oldmodel
Source context: 822 downloads · Type Workflows · Base model Flux.1 D
Checkpoint · 11.8 GB · GGUF · fp16 · Civitai · 1452850
t5-v1_1-xxl-encoder-Q8_0 (1).gguf
Nicht aufgelöstText encoder · Unknown
BasicGuider
Nicht aufgelöstKnotenpaket · Unknown
BasicScheduler
MöglichKnotenpaket · Unknown
CLIPTextEncode
MöglichKnotenpaket · Unknown
DualCLIPLoaderGGUF
MöglichKnotenpaket · Unknown
FluxGuidance
Nicht aufgelöstKnotenpaket · Unknown
ImageScaleToTotalPixels
MöglichKnotenpaket · Unknown
KSamplerSelect
MöglichKnotenpaket · Unknown
LoadImage
MöglichKnotenpaket · Unknown
Power Lora Loader (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
RandomNoise
Nicht aufgelöstKnotenpaket · Unknown
SamplerCustomAdvanced
Nicht aufgelöstKnotenpaket · Unknown
SaveImage
MöglichKnotenpaket · Unknown
UnetLoaderGGUF
MöglichKnotenpaket · Unknown
VAEDecode
MöglichKnotenpaket · Unknown
VAEEncode
MöglichKnotenpaket · Unknown
VAELoader
MöglichKnotenpaket · Unknown