Loading
Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
Here is a starter workflow for the newly released Flux 2 Dev by the ComfyUI team.
Laufzeitprofil
Quellenbeschreibung
Here is a starter workflow for the newly released Flux 2 Dev by the ComfyUI team.
This workflow is designed to get you up and running quickly with the new architecture. It handles standard Text-to-Image generation but also includes a setup for Reference Image Conditioning (Multimodal input).
Workflow Features:
Standard Generation: calibrated for Flux 2 Dev.
Reference Inputs: I have included ReferenceLatent nodes connected to LoadImage inputs. This allows you to prompt using images (similar to IP-Adapter/Variations) combined with text.
Note: As written in the workflow notes, simply Bypass (Ctrl+B) the Reference nodes if you only want to do pure Text-to-Image.
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This Flux 2 Dev workflow is for text-to-image generation: it combines text prompts with optional reference images through `LoadImage` and `ReferenceLatent`, then generates images and includes a `SaveImage` node.
For text-only generation, bypass the Reference nodes with Ctrl+B.
Vorschlag · nicht geprüft
For reference-image conditioning, upload images to the `LoadImage` nodes so they can be used with text prompts through `ReferenceLatent`.
Vorschlag · nicht geprüft
Inputs are a text prompt and optional reference images loaded through `LoadImage`.
The workflow generates images and includes a `SaveImage` node.
Place `flux2_dev_fp8mixed.safetensors`, `mistral_3_small_flux2_fp8.safetensors`, and `flux2-vae.safetensors`, or equivalents, in your ComfyUI models folder.
Vorschlag · nicht geprüft
Load the workflow, select checkpoints in the Loaders, and queue the prompt.
Vorschlag · nicht geprüft
The listed model files are `flux2_dev_fp8mixed.safetensors`, `mistral_3_small_flux2_fp8.safetensors`, and `flux2-vae.safetensors`.
Listed node types include `BasicGuider`, `CLIPLoader`, `CLIPTextEncode`, `EmptyFlux2LatentImage`, `Flux2Scheduler`, `FluxGuidance`, `ImageScaleToTotalPixels`, `KSamplerSelect`, `LoadImage`, and `RandomNoise`.
Other listed node types are `ReferenceLatent`, `SamplerCustomAdvanced`, `SaveImage`, `UNETLoader`, `VAEDecode`, `VAEEncode`, and `VAELoader`.
The default resolution is 1024x1024.
The listed base model is `Flux.2 D`, and the workflow version is `v1.0`.
Before use, verify that your ComfyUI installation includes the listed node types.
Vorschlag · nicht geprüft
No license is specified for this workflow.
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
3 AuszügeSource context: 1292 downloads · Type Workflows · Base model Flux.2 D
Resolution: Defaults set to 1024x1024.
Required Models: To use this workflow without errors, ensure you have the following models (or their equivalents) in your ComfyUI models folder(model links are included in the workflow):
UNET/Diffusion: flux2_dev_fp8mixed.safetensors
CLIP: mistral_3_small_flux2_fp8.safetensors
VAE: flux2-vae.safetensors
How to use:
Load the workflow.
Ensure your checkpoints are selected in the Loaders.
(Optional) Upload images to the "Load Image" nodes to test the reference capabilities, or mute them for standard prompting.
Queue Prompt!
Enjoy exploring Flux 2! Let me know if you run into any issues.
Remaining hardware or download-size estimates are not available yet.
Anforderungen
flux2_dev_fp8mixed.safetensors
GefundenCheckpoint · 33.0 GB · SAFETENSORS · fp8 · pruned · Unknown
flux2-vae.safetensors
Datei ungeprüftVAE · Unknown
Source context: 1104 downloads · Type Workflows · Base model Flux.2 D
Source context: 1057 downloads · Type Workflows · Base model Flux.2 D
Text encoder · 16.8 GB · SAFETENSORS · fp8 · pruned · Unknown
