Z-Image-Turbo_Oldschool-Hud-Graphics
Create Oldschool Hud Graphics with a LoRA and Z-Image Turbo. Use a LoRA to create unique styles, characters or looks.
概要
This workflow generates retro, old‑school HUD graphics from text prompts by combining a style LoRA with a turbo sampler for rapid iteration. The "Oldschool Hud Graphics" LoRA steers the base checkpoint toward geometric UI motifs—reticles, gridlines, rings, readouts—while the Z‑Image Turbo node accelerates sampling for fast previews and quick style exploration. BatchImagesNode lets you spin up variations in one pass, and SaveImage captures your chosen frames. When you’re ready to animate, CreateVideo and SaveVideo assemble your batch into a short motion clip.
入力するもの
- ワークフローを読み込み中
ComfyUI で実行できます。 このワークフローはこのページでは実行できません。すべてが読み込まれた状態でComfy Cloudで開くか、ご自身のComfyUI用にダウンロードしてください。
Cloudで試す例を試す
よくある質問
Use a checkpoint that matches the LoRA’s architecture (e.g., SD 1.5 LoRA with an SD 1.5 checkpoint, SDXL LoRA with an SDXL checkpoint). Check the LoRA’s model card or filename for its target version. Mixing versions will reduce quality or fail to load.
Adjust the LoRA weight (lower for subtle, higher for strong). Refine prompts to emphasize geometry (reticle, grid, ring, UI readouts) and use a negative prompt to suppress photoreal features. If outputs feel busy, slightly lower CFG or reduce steps to simplify shapes.
Increase sampling steps modestly in Z‑Image Turbo, keep CFG moderate, and try a resolution that matches your final layout (avoid extreme upscales in one pass). Tighten the prompt to fewer, clearer elements (e.g., one reticle + one grid) and avoid conflicting style terms.
After generating a batch with BatchImagesNode, connect the sequence to CreateVideo, set your frame rate and ordering, then export with SaveVideo. This compiles your HUD variants into a short motion clip for previews or social posts.