Aller au contenu
WorkflowVérifiéExterne
Télécharger

Better Z Image Turbo

initial release - NSFW LoRA disabled (even though the strength is so low it only adds subtle detail)

FamilleZ-ImageVersionRelease 3067466 — betterZImageTurbo_v1.jsonEstimé VRAMNot yet characterizedUnratedClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Vérifié
Version
betterZImageTurbo_v1.json
Source
Civitai
Mis à jour
3 nov. 2026

What you need

Model files
12.6 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Exigences

Modèles

7

Commentaire généré par l’IA

Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.

Objectif

  • Better Z Image Turbo is a ComfyUI workflow for generating images from text conditioning with the ZImageTurbo base model; it uses a diffusion model, text encoder, VAE, and LoRA files, then decodes and saves image output.

Flux

  • The listed nodes cover text encoding, latent-image setup, sampling, LoRA loading, VAE decoding, and image saving through CLIPTextEncode, EmptySD3LatentImage, KSampler, LoraLoaderModelOnly, VAEDecode, and SaveImage.

Entrées et sorties

  • The listed model files are ae.safetensors, qwen_3_4b.safetensors, and z_image_turbo_bf16.safetensors.

  • The listed LoRA files are HI8.safetensors, Olympus.safetensors, Z-Detail-Slider.safetensors, and NSFW_master_ZIT_000017532.safetensors.

  • VAEDecode and SaveImage are included for image decoding and saving.

Installation

  • Version v1 is described as an official ComfyUI template with no custom nodes.

Dépendances

  • The workflow lists CLIPLoader, CLIPTextEncode, ConditioningZeroOut, EmptySD3LatentImage, KSampler, and LoraLoaderModelOnly.

  • Other listed node types are MarkdownNote, SaveImage, UNETLoader, VAEDecode, and VAELoader.

Configuration

  • The listed LoRA strengths are HI8 at 0.04, Olympus at 0.20, Z-Detail-Slider at 0.69–1.00, and NSFW_master_ZIT at 0.07; NSFW_master_ZIT is off.

  • To follow the described visual contrast, choose Ultra Flux 4k VAE for added detail or ae.safetensors for a more smoothed effect.

    Suggestion · non vérifié

Précautions

  • NSFW_master_ZIT is off at 0.07; the description says 1.00–3.00 is for actual NSFW output, with 2.00 as a middle-ground setting.

  • The INT8 note says v2 requires ComfyUI v0.27.0; this listing is v1, so verify which ComfyUI version and model files your setup expects.

    Suggestion · non vérifié

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source
CivitaiPrincipalVersion 3067466
civitai.com/models/2728769

Vérifié 3 nov.

Workflow instructions

Author notes from betterZImageTurbo_v1.json · selected release

## Report workflow issue If you found any issues when running this workflow, [report template issue here](https://github.com/Comfy-Org/workflow_templates/issues) ## Model links **text_encoders** - [qwen_3_4b.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors) **diffusion_models** - [jibMixZIT_v10.safetensors](https://civitai.com/models/2231351/jib-mix-zit?modelVersionId=2511897) **vae** - [diffusion_pytorch_model.safetensors](https://huggingface.co/Owen777/UltraFlux-v1/blob/main/vae/diffusion_pytorch_model.safetensors) **loras** - [HI8.safetensors](https://civitai.com/models/1134895/2000s-analog-core?modelVersionId=2456725) - [Olympus.safetensors](https://civitai.com/models/2212121/olympus-ultrareal?modelVersionId=2490572) - [Z-Detail-Slider.safetensors](https://civitai.com/models/2234266/zit-detail-slider?modelVersionId=2515203) **optional lora - bypassed by default** - [NSFW_master_ZIT_000017532.safetensors](https://civitai.com/models/667086/nsfw-master?modelVersionId=2904324) Model Storage Location ``` 📂 ComfyUI/ ├── 📂 models/ │ ├── 📂 text_encoders/ │ │ └── qwen_3_4b.safetensors │ ├── 📂 diffusion_models/ │ │ └── z_image_turbo_bf16.safetensors │ └── 📂 vae/ │ │ └── ae.safetensors │ └── 📂 loras/ │ └── HI8.safetensors │ └── Olympus.safetensors │ └── Z-Detail-Slider.safetensors │ └── NSFW_master_ZIT_000017532.safetensors ```

Download files

Artefacts du modèle

2 artefacts

betterZImageTurbo_v1.json

json · 16,9 KB · SHA-256 e014e883ae8c…a4d4 · Civitai

Download file

betterZImageTurbo_v1.json

json · 16,9 KB · SHA-256 e014e883ae8c…a4d4

Download file

Extraits de sources

3 extraits

Source context: 498 downloads · Type Workflows · Base model ZImageTurbo

Source context: 417 downloads · Type Workflows · Base model ZImageTurbo

Source context: 276 downloads · Type Workflows · Base model ZImageTurbo