Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Here is a starter workflow for the newly released Flux 2 Dev by the ComfyUI team.
Runtime profile
Source description
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.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
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.
Suggestion · not verified
For reference-image conditioning, upload images to the `LoadImage` nodes so they can be used with text prompts through `ReferenceLatent`.
Suggestion · not verified
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.
Suggestion · not verified
Load the workflow, select checkpoints in the Loaders, and queue the prompt.
Suggestion · not verified
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.
Suggestion · not verified
No license is specified for this workflow.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource 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.
Requirements
Checkpoint · 33.0 GB · SAFETENSORS · fp8 · pruned · Unknown
flux2-vae.safetensors
File unverifiedVAE · 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
