Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Profil d'exécution
Description de la source
Anima Turbo + CFG 1 Negative prompt
A lightweight, beginner-friendly workflow for Anima Turbo that allows negative prompting at CFG 1 using NegPip .
Turbo models are fast, but running at CFG 1 means the negative prompt box has no effect. This workflow solves that problem using NegPip, which allows you to apply negative concepts directly inside the positive prompt.
How NegPip Works
Instead of using the negative prompt box, place unwanted concepts in the positive prompt with a negative weight:
(blurry:-1)
(low quality:-2)
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.
This workflow is for generating Anima Turbo images from a positive text prompt at CFG 1; it uses NegPip for negatively weighted concepts and outputs a generated image with saved metadata.
At CFG 1, place unwanted concepts in the positive prompt with weights such as `(blurry:-1)`, `(low quality:-2)`, or `(text:-4)`; NegPip interprets them as negative conditioning.
The workflow includes a preconfigured Anima Turbo LoRA, NegPip integration, an Impact Wildcard Encoder, metadata saving, and a simple single-pass generation pipeline.
Use a positive text prompt, optionally including negative-weight terms and wildcard tokens such as `__WildcardName__`.
The workflow produces a generated image and includes metadata saving.
Dioxide published this v1.0 workflow for the Anima base model.
The listed model files are `anima_baseV10.safetensors`, `anima-turbo-lora-v0.1.safetensors`, `qwen_3_06b_base.safetensors`, and `qwen_image_vae.safetensors`.
The workflow also calls for the `comfyui-image-saver` node pack.
Start with CFG 1, 8–12 steps, and the Euler, Euler Ancestral, or ER-SDE sampler.
Suggestion · non vérifié
Use up to 1536×1536 resolution; the source describes about 1.5 megapixels as a balance between quality and speed.
Suggestion · non vérifié
Create `.txt` wildcard files in `ComfyUI/custom_nodes/comfyui-impact-pack/custom_wildcards` and call them with `__WildcardName__`; randomization is tied to the image seed by default.
Before use, verify that `anima-turbo-lora-v0.1.safetensors` is available; its file identity is not confirmed.
Suggestion · non vérifié
No use license is provided in the listed source details.
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
3 extraitsSource context: 280 downloads · Type Workflows · Base model Anima
(text:-4)
NegPip interprets these negative weights as negative conditioning, allowing you to steer the image away from unwanted features while keeping the speed benefits of CFG 1 turbo generation.
Don't be afraid to use larger values. In my testing, weights up to ±4 can produce strong results with Anima without frying the image.
Recommended Settings
CFG: 1
Steps: 8–12
Sampler: Euler / Euler Ancestral / ER-SDE
Resolution: Up to 1536×1536 works, but ~1.5 megapixels is a good sweet spot between quality and speed in my opinion
Included Features
Anima Turbo LoRA preconfigured
NegPip integration
Impact Wildcard Encoder
Metadata saving
Simple single-pass generation pipeline
Easy LoRA and wildcard expansion
Wildcards
Create .txt wildcard files in:
ComfyUI/custom_nodes/comfyui-impact-pack/custom_wildcards
Then call them in your prompt using:
WildcardName
Wildcard randomization is tied to the image seed by default for reproducible generations.
Limitations
This workflow is intentionally minimal. The goal is to provide a clean, reliable starting point for Anima Turbo users who want the speed of CFG 1 generation without giving up the control that negative prompting provides.
Estimation des besoins VRAM
Estimation indisponible
242 MB sur 1 de 4 fichiers de modèle. Total des fichiers du modèle + 25 % de surcharge de chargement + 2 Go de tampon d'exécution, arrondi à l'unité supérieure.
Exigences
Exigences 5Checkpoint · Civitai · 2458426
Sources possibles
anima-turbo-lora-v0.1.safetensors
PossibleLoRA · Unknown
Text encoder · Civitai · 2695493
Sources possibles
VAE · 242 MB · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
Sources possibles
Pack de nœud · Registry
Source context: 248 downloads · Type Workflows · Base model Anima
Source context: 246 downloads · Type Workflows · Base model Anima
