Moving to Anima from Illustrious has been daunting due to its reliance upon lengthy natural language descriptions to get quality results, whereas with Illustrious you relied upon tags with highly defined concepts as...
Laufzeitprofil
Quellenbeschreibung
Moving to Anima from Illustrious has been daunting due to its reliance upon lengthy natural language descriptions to get quality results, whereas with Illustrious you relied upon tags with highly defined concepts as "building blocks".
I created this workflow to help me navigate this, by using a prompting category approach to get a better defined structure.
Part of the reason for this approach is that I enjoy tweaking prompts and using wildcards, but natural language is easy to entangle. So by keeping it all segmented, it allows me to adjust segments of the prompt freely and without issue.
Included with the workflow are some example wildcard files, which contain a small number of random prompts I generated with ChatGPT to help get started.
v1.1 adds a number of automated and manual prompting toggles to improve user experience. Most notably, category headers no longer appear unless that category is actually used, and you can now disable them entirely if you want more manual control.
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Use this Anima workflow to organize natural-language prompt details into categories and wildcard segments, so you can adjust each part while preparing an image-generation prompt.
Keeping prompt parts separate lets you adjust each segment without tangling the rest of the text.
Example wildcard files include a small number of randomly generated starter prompts made with ChatGPT.
Work with natural-language prompt text and wildcard choices; the workflow organizes them into separate prompt segments for individual editing.
The listed release is v1.0 and names Anima as its base model.
Model files listed are anima_baseV10.safetensors, qwen_3_06b_base.safetensors, and qwen_image_vae.safetensors.
Node packs listed are comfyui-impact-pack, comfyui-kjnodes, comfyui-prompt-reader-node, comfyui-vslinx-nodes, and rgthree-comfy.
The source also names basic_data_handling and was-ns as node packs; confirm which packages these names refer to before setup.
Vorschlag
The v1.1 description lists automated and manual prompting toggles; category headers appear only for used categories and can be turned off.
The listing identifies v1.0 while the description discusses v1.1 controls; check your version before relying on those options.
Vorschlag · nicht geprüft
No license is listed in the source details, so check the usage terms before use.
Vorschlag
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 522 downloads · Type Workflows · Base model Anima
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
242 MB über 1 von 3 Modell-Dateien. Gesamtmodell-Dateien + 25% Ladeaufwand + 2 GB Ausführungs-Puffer, aufgerundet.
Anforderungen
10 AnforderungenCheckpoint · Civitai · 2458426 · anima-base-v1.0.safetensors
Text encoder · Civitai · 2695493
VAE · 242 MB · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
basic_data_handling
Nicht aufgelöstKnotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
was-ns
Nicht aufgelöstKnotenpaket · Registry