【FLUX】IMG to IMG — v4.3

【FLUX】IMG to IMG — v4.3 is for turning an input image and text prompt into a generated image in ComfyUI with the Flux.1 D model, with an option to view an upscaled result.

Load an image, write a prompt, generate an image, and use the slider to view the normal and upscaled results.

Inputs include an image, a text prompt, and the Flux.1 D model; outputs are saved images.

Three LoRA slots provide individual on/off toggles and strength controls, and additional LoRA modules can be connected.

Saved images include all generation parameters for online publishing and remixing.

In ComfyUI, enable "Use Nodes V2 (Vue)" in Settings, refresh the page, and then load the workflow.

Install `ComfyUI-UmeAiRT-Toolkit` through ComfyUI Manager by searching `UmeAiRT`, or use the UmeAiRT Auto-Installer.

Named node entries include `Image Comparer (rgthree)`, `UnetLoaderGGUF`, `UltimateSDUpscale`, `CLIPTextEncode`, `ConditioningZeroOut`, `LoadImage`, `mxSlider`, `Text Input [Dream]`, `BasicGuider`, `FluxGuidance`, `UpscaleModelLoader`, `Fast Groups Bypasser (rgthree)`, `KSampler]`

Additional named node entries include `VAEDecode`, `workflow>LoRA - 3`, `Save Images // RvTools`, `ModelSamplingFlux`, `workflow>LoRA - 1`, `DualCLIPLoaderGGUF`, `BasicScheduler`, `workflow>LoRA - 2`, `Image Size to Number`, `VAEEncode`, `VAELoader`, `SamplerCustomAdvanced`, `JW]

For the manual Base setup, the listed files are `flux1-dev-fp8.safetensors` or `flux1-dev-fp16.safetensors` in `ComfyUI\models \ diffusion_models`, `clip_l.safetensors` in `ComfyUI\models\clip`, `t5xxl_fp8_e4m3fn.safetensors` or `ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.s

Toggle the built-in SeedVR2 upscaler on or off.

The auto version supports automatic model downloads.

Enable "Use Nodes V2 (Vue)" before loading; otherwise the workflow may have display problems.

Before using the Base or GGUF setup, verify the listed filenames and ComfyUI folders in your local installation.

Suggestion · non vérifié