[flux1-kontext-dev] Flux Kontext (image editing) model

This Flux Kontext workflow is for image editing: it accepts a source image and text input, processes them with Flux guidance and sampling, and saves an image output.

The flow loads and scales an image, handles a reference latent, encodes text, applies Flux guidance, samples, runs VAE encode and decode steps, and saves the result.

Use LoadImage for a source image and CLIPTextEncode for text input.

SaveImage is the named step for saving the image output.

The listing identifies Nouvo Ai as the publisher and Flux.1 Kontext as the base model.

This item is listed as a workflow, not a Pipe.

The listed model files are ae.safetensors, clip_l.safetensors, flux1-kontext-dev.safetensors, and t5xxl_fp16.safetensors.

Named processing steps include BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoader, EmptySD3LatentImage, FluxGuidance, FluxKontextImageScale, ImageScaleBy, KSamplerSelect, and LoadImage.

Other named steps are ModelSamplingFlux, RandomNoise, ReferenceLatent, SamplerCustomAdvanced, SaveImage, UNETLoader, VAEDecode, VAEEncode, and VAELoader.

The listed file roles are VAE for ae.safetensors, UNet for flux1-kontext-dev.safetensors, and text encoders for clip_l.safetensors and t5xxl_fp16.safetensors.

Before use, verify that the listed model files and named processing steps are available in your environment.

Vorschlag · nicht geprüft

If it does not run, the listing says to try it in Nordy.

Vorschlag · nicht geprüft