Be sure to upload your image with my workflow. i want to see your results :)
Laufzeitprofil
Quellenbeschreibung
Be sure to upload your image with my workflow. i want to see your results :)
Klein model Notice: i have since revised my workflow for klein model, but have not yet updated it to my page. I may not upload it either since there hasn't been people uploading images in the workflow page. Though i may distribute the updated klein workflow if someone is actively uploading their results/images to my workflow page. Im just saying this if anyone is wondering/noticing a quality difference between my current Klein images compared to the results of the posted workflow. its still a great workflow to start off.
Z-IMAGE: This is a lite/minimal version from the one i usually use. This is faster and simpler than the "full" version. Nonetheless, it still produces great images. I suggest using the model and loras i used which can be found in my post. Also, if you are using detail slider lora, turn it down from 1.00 to 0.50 to make it brighter while still maintaining good detail. the workflow i uploaded is meant to be a foundation that you can build upon. it has most of the tools that you need to get good images already without being too complicated.
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This workflow is for creating image results from an uploaded image using Z-Image and Flux.2 Klein 9B.
Input: an image uploaded with the workflow.
Output: image results from the workflow.
Find it on Civitai, where it is published by Mrpopo714.
The listed model files are: ema_vae_fp16.safetensors, flux-2-klein-9b-nvfp4.safetensors, flux2-vae.safetensors, qwen_3_8b_fp8mixed.safetensors, and seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors.
The listed node packs are: comfyui-detail-daemon, comfyui-image-saver, RES4LYF, and seedvr2_videoupscaler.
Check that the listed filenames and node-pack names match the items available in your setup before use.
Vorschlag
The author describes this as a lite, minimal version that is simpler than the full version and a foundation to build on.
If you use a detail slider LoRA, the author suggests lowering it from 1.00 to 0.50 for a brighter result while maintaining detail.
Vorschlag · nicht geprüft
No usage license is listed, so check the usage rights before using the workflow.
Vorschlag
The posted workflow may not include a later Klein revision mentioned by the author, so check the Civitai page for the version you intend to use.
Vorschlag
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 2231 downloads · Type Workflows · Base model Flux.2 Klein 9B
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
8,07 GB über 1 von 6 Modell-Dateien. Gesamtmodell-Dateien + 25% Ladeaufwand + 2 GB Ausführungs-Puffer, aufgerundet.
Anforderungen
9 Anforderungenema_vae_fp16.safetensors
KonfliktVAE · Unknown
flux-2-klein-9b-nvfp4.safetensors
Nicht aufgelöstCheckpoint · Unknown
VAE · Hugging Face · Comfy-Org/flux2-dev
qwen_3_8b_fp8mixed.safetensors
GefundenText encoder · 8.07 GB · SAFETENSORS · fp16 · Hugging Face · Comfy-Org/flux2-klein-9B
seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors
Nicht aufgelöstCheckpoint · Unknown
seedvr2_videoupscaler
Nicht aufgelöstUpscaler · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry