Aller au contenu
WorkflowPrésentéExterne
Ouvrir la source

Qwen Image simple GGUF workflow (16VRAM 32RAM) — v1.0

How it's going gguffers, it's time to spit out some super simple and based txt2img workflow for goofy GGUF users like me who often struggle with installation or just don't care about advanced features and want just...

Sourcecivitai.com/models/1853153
TâcheTexte en imageFamilleQwen-ImageEstimé VRAMNot yet characterizedBClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Présenté
Source
Civitai
Mis à jour
2 oct. 2026

Description de la source

How it's going gguffers, it's time to spit out some super simple and based txt2img workflow for goofy GGUF users like me who often struggle with installation or just don't care about advanced features and want just to touch a model.

Requirements:

ComfyUI v0.3.49+

ComfyUI Manager v3.35+

16GB of VRAM and 32GB of RAM (or less, if you will choose lower quants)

Installation:

Download model files:

Main model (drop into ComfyUI\models\unet). Options: choose any from Q5_1, Q5_K_M, Q5_K_S or bigger. I prefer 5_1.

Text model (drop into ComfyUI\models\text_encoders). Options: UD_Q5_K_XL, Q5_K_M or bigger. I took Q6_K.

VAE

Download and open this workflow in ComfyUI.

Go to "Manager" - "Custom Nodes Manager" and install "ComfyUI-GGUF" v1.1.3 or above (older versions will blow an error "Unexpected text model architecture type"). Restart the ComfyUI.

Usage:

Choose some resolution: any divided by 16 should work, but native options listed inside the workflow note (x1328 and its variations) are the best. Text is better render at native resolution.

Choose number of steps and a sampler:

15-20 steps for Euler beta/simple (1-4 cfg), Euler_cfg_pp simple (1cfg)

8 steps with DDIM beta (1-2 cfg). If you're crazy bastard like me, you can even set 5 steps and try your luck (lightning lora is not required).

If you experience crashes at the VAE Decode node, try using lower quants (if Q5_1 crashes, check the Q5_K_S).

If you have any other errors, do a clean install of ComfyUI and Manager and repeat.

Things tested on ComfyUI Windows portable edition v0.3.49 with 32RAM and 16VRAM 5060Ti.

What you need

Hardware and download-size estimates are not available yet.

Exigences

Modèles

3

  • Qwen_Image_Distill-Q5_1.gguf

    Non résolu

    Checkpoint · Unknown

  • Qwen_Image-VAE.safetensors

    Non résolu

    VAE · Unknown

  • Qwen2.5-VL-7B-Instruct-Q6_K.gguf

    Non résolu

    Text encoder · Unknown

Packs de nœuds

1

  • comfyui-gguf

    Possible

    Pack de nœud · Registry

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

  • Use this ComfyUI workflow to turn a text prompt into an image output, using the Qwen model, text encoder, VAE, resolution, sampler, step count, and CFG value as inputs.

Flux

  • The workflow loads the GGUF model, text encoder, and VAE, encodes your prompt, creates a latent image, samples it, decodes it, and sends the result to SaveImage.

  • Open it in ComfyUI, choose a resolution and sampling settings, and use the text-to-image path.

Entrées et sorties

  • Provide a text prompt, resolution, step count, sampler, and CFG value.

  • The image-generation path includes CLIPTextEncode, EmptySD3LatentImage, KSampler, VAEDecode, and SaveImage.

Installation

  • Use ComfyUI v0.3.49 or later and ComfyUI Manager v3.35 or later; the listed requirements include 16 GB of VRAM and 32 GB of RAM, with lower quants also mentioned.

  • Install ComfyUI-GGUF v1.1.3 or later through Custom Nodes Manager, then restart ComfyUI; older versions are reported to produce an “Unexpected text model architecture type” error.

Dépendances

  • The listed model files are Qwen_Image_Distill-Q5_1.gguf, Qwen_Image-VAE.safetensors, and Qwen2.5-VL-7B-Instruct-Q6_K.gguf.

  • Place Qwen_Image_Distill-Q5_1.gguf in ComfyUI\models\unet and Qwen2.5-VL-7B-Instruct-Q6_K.gguf in ComfyUI\models\text_encoders.

Configuration

  • Choose a resolution divisible by 16; x1328 and its variations are listed as native options, and text is better rendered at native resolution.

  • Sampling options include 15–20 steps with Euler beta/simple at 1–4 CFG, Euler_cfg_pp simple at 1 CFG, or DDIM beta at 8 steps and 1–2 CFG.

  • Listed main-model options include Q5_1, Q5_K_M, Q5_K_S, or larger; text-model options include UD_Q5_K_XL, Q5_K_M, or larger.

Précautions

  • No checksums are listed for the three model files, so verify the downloaded files before setup.

    Suggestion · non vérifié

  • If VAE Decode crashes, try a lower quant, such as Q5_K_S after Q5_1; for other errors, clean-install ComfyUI and Manager and repeat.

    Suggestion · non vérifié

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source
CivitaiPrincipal
civitai.com/models/1853153

Vérifié 19 juil.

Extraits de sources

1 extrait
Note19 juil.civitai.com/models/1853153

Source context: 432 downloads · Type Workflows · Base model Qwen