This is a 9 column prompt grid for SDXL/PonyXL with LoRA support. It generates 9 images based on 1 seed and the 9 prompts that you enter. It has an on/off toggle for each column in case you don't need to use all of...
Profil d'exécution
Description de la source
This is a 9 column prompt grid for SDXL/PonyXL with LoRA support. It generates 9 images based on 1 seed and the 9 prompts that you enter. It has an on/off toggle for each column in case you don't need to use all of them. I use it to:
-Test the weight of certain words, like muscular to (muscular:1.2) to (muscular:1.4).
-See how adjectives and negatives affect the same prompt.
-And my favorite, shuffling the lines of a prompt into 9 different groups to see which order turns out the best. I use ChatGPT to shuffle it for me:
Please take the following lines and shuffle them into 9 different groups, including the commas: Crocodile_Dundee, punching a kangaroo, in a boxing ring, dynamic, action, documentary,
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.
Use this nine-column ComfyUI workflow to compare SDXL/PonyXL prompt variations: enter one seed and nine prompts, choose which columns are on or off, and generate nine images with LoRA support.
Compare word weights such as muscular, (muscular:1.2), and (muscular:1.4) with the same prompt.
Compare how adjectives and negatives affect the same prompt, or compare nine shuffled prompt-line orders.
Inputs are one seed, nine prompts, and an on/off choice for each column.
The workflow generates nine images based on the seed and prompts.
The listed model files are EpicRealismXLv7.safetensors, PonyXL Body Weight Slider v1.safetensors, PonyXL Muscle Slider v1.safetensors, and SDXLVAEFP16.safetensors.
The listed node types are CheckpointLoaderSimple, CLIPTextEncodeSDXL, KSampler, LoraLoader, CLIPSetLastLayer, VAELoader, VAEDecode, EmptyLatentImage, and SaveImage.
For fewer than nine prompt variations, switch off the columns you do not need.
Suggestion · non vérifié
For prompt-order comparisons, enter nine groups made by shuffling the prompt lines, including their commas.
Suggestion · non vérifié
Confirm that the listed model files and node types are available in your ComfyUI setup before running.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 190 downloads · Type Workflows · Base model Other
Hardware and download-size estimates are not available yet.
Exigences
EpicRealismXLv7.safetensors
Non résoluCheckpoint · Unknown
PonyXL Body Weight Slider v1.safetensors
Non résoluLoRA · Unknown
PonyXL Muscle Slider v1.safetensors
Non résoluLoRA · Unknown
SDXLVAEFP16.safetensors
Non résoluVAE · Unknown
VAEDecode
PossibleVAE · Unknown
VAELoader
PossibleVAE · Unknown
CheckpointLoaderSimple
PossiblePack de nœud · Unknown
CLIPSetLastLayer
PossiblePack de nœud · Unknown
CLIPTextEncodeSDXL
PossiblePack de nœud · Unknown
EmptyLatentImage
PossiblePack de nœud · Unknown
KSampler
PossiblePack de nœud · Unknown
LoraLoader
PossiblePack de nœud · Unknown
SaveImage
PossiblePack de nœud · Unknown