Playground v2.5 with Face_Detailer [ComfyUi] — v1.0

Use this ComfyUI workflow to generate Playground 2.5 images with Face Detailer: enter up to five separate face prompts and receive generated faces.

The workflow combines the Playground 2.5 model with an SD_1.5 model for Face Detailer.

Give each face its own prompt; Face Detailer can generate up to five different faces.

Download version v1.0 from the Civitai page and open it in ComfyUI.

Sugestão · não verificado

Named node components include MaskPreview+, CLIPSetLastLayer, ModelSamplingContinuousEDM, SaveImage, ImpactSimpleDetectorSEGS, CLIPTextEncode, EmptyLatentImage, CheckpointLoaderSimple, UltralyticsDetectorProvider, DetailerForEach, ImpactSEGSOrderedFilter, SAMLoader, KSampler (Eff

Listed model files include playground-v2.5-1024px-aesthetic.fp16.safetensors, epicrealism_naturalSinRC1VAE.safetensors, epicrealism_pureEvolutionV5-inpainting.safetensors, juggernautXL_v7Rundiffusion.safetensors, bbox/face_yolov8n_v2.pt, and sam_vit_b_01ec64.pth.

The workflow requires Adetailer, Juggernaut XL, and epiCRealism (pure Evolution-inpainting).

Use the SD_1.5 model rather than the Playground model for Face Detailer; the description says this choice was made for face results, especially skin appearance.

Before setup, verify the source and filename for MaskPreview+, playground-v2.5-1024px-aesthetic.fp16.safetensors, and epicrealism_naturalSinRC1VAE.safetensors; no provider identifier or checksum is listed for these items.

Sugestão · não verificado

Review the Civitai page for setup details before use; the listing has no separate description.

Sugestão · não verificado