Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
SIMPLE FLUX DEV WORKFLOW by weshouldhaveshotguns
Profil d'exécution
Description de la source
SIMPLE FLUX DEV WORKFLOW by weshouldhaveshotguns
This workflow is designed to provide a straightforward, intuitive approach to using Flux Dev in ComfyUI. My goal was to create a setup that not only works well but also helps users understand what each node does and why it's there, making it easier for them to customize and experiment on their own.
The workflow includes links to all the required files, a settings rundown, and best practices for resolutions and prompts, with guidance on how settings like FluxGuidance, steps, and samplers influence output. Whether you're new to AI art or have some experience, this workflow will give you a solid foundation in Flux, enabling you to quickly become proficient and even pick up a few intermediate tips. It’s not the ultimate workflow—there’s always more to learn—but it’s well-optimized, thoughtfully organized, and a great starting point for both learning and creation.
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.
This ComfyUI workflow is for creating Flux Dev images from text prompts and resolution settings. It can adjust FluxGuidance, steps, sampler choices, and optional LoRA settings for character or style tweaks, then save the resulting images.
The listed nodes cover prompt text encoding, latent-image setup, model loading, guidance, scheduling, sampling, decoding, and image saving.
Use a text prompt, resolution, FluxGuidance, steps, sampler choices, and optional LoRA settings; the workflow produces a saved image.
Comfy Manager installation instructions are included for this ComfyUI workflow.
The description includes links to the required files.
The listed model files are ae.safetensors, clip_l.safetensors, flux1-dev.safetensors, and t5xxl_fp8_e4m3fn.safetensors.
Listed node components include BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoader, EmptyLatentImage, FluxGuidance, and KSamplerSelect.
Additional listed components are Power Lora Loader (rgthree), RandomNoise, SamplerCustomAdvanced, SaveImage, UNETLoader, VAEDecode, and VAELoader.
The included guidance explains how resolution, FluxGuidance, steps, and samplers influence output.
The Power Lora Loader (rgthree) can add custom character and style tweaks.
Use one character LoRA at a time; combining two character LoRAs is discouraged.
Suggestion · non vérifié
Before running it, verify that the listed model files and node components are available in ComfyUI.
Suggestion · non vérifié
A license is not specified for this workflow.
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 702 downloads · Type Workflows · Base model Flux.1 D
New in v2 :
LoRA Magic Unlocked : v2 brings LoRA support with a Power LoRA Loader , letting you add custom character and style tweaks. Layer multiple LoRAs if you dare, but balance them carefully.
Forbidden Note : Avoid combining two character LoRAs unless you want to summon a "cursed lovechild." Stick to one character LoRA at a time for best results.
Other Additions :
Comfy Manager Setup : Added installation instructions for an easy setup.
Workflow Rundown Upgrade : Expanded with tips on using the Power LoRA Loader to its fullest.
Why v2? v2 gives you more creative freedom and control, letting you explore LoRAs without overcomplicating the Flux workflow.
Estimation des besoins VRAM
Estimation indisponible
27,0 GB sur 3 de 7 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 18VAE · Unknown
Text encoder · 235 MB · SAFETENSORS · Unknown
DualCLIPLoader
Non résoluText encoder · Unknown
Checkpoint · 22.2 GB · SAFETENSORS · fp32 · full · Unknown
Text encoder · 4.56 GB · SAFETENSOR · fp8 · Unknown
VAEDecode
Non résoluVAE · Unknown
VAELoader
Non résoluVAE · Unknown
BasicGuider
Non résoluPack de nœud · Unknown
BasicScheduler
PossiblePack de nœud · Unknown
CLIPTextEncode
PossiblePack de nœud · Unknown
EmptyLatentImage
Pack de nœud · Unknown
FluxGuidance
Non résoluPack de nœud · Unknown
KSamplerSelect
PossiblePack de nœud · Unknown
Power Lora Loader (rgthree)
Non résoluPack de nœud · Unknown
RandomNoise
Non résoluPack de nœud · Unknown
SamplerCustomAdvanced
Non résoluPack de nœud · Unknown
SaveImage
PossiblePack de nœud · Unknown
UNETLoader
PossiblePack de nœud · Unknown
