Some people have modified and used my "Consistency characters" workflow to generate scenes instead of characters. Since "Consistency characters" is getting more and more complicated with updates, I decided to make a...
Runtime profile
Source description
Some people have modified and used my "Consistency characters" workflow to generate scenes instead of characters. Since "Consistency characters" is getting more and more complicated with updates, I decided to make a separate workflow for scenes to make it easier for people to adapt it for themselves.
It's very simplistic and doesn't have many features. I haven't experimented much with scenes myself, but it works more or less.
Estimated VRAM requirement
Estimate unavailable
6.99 GB across 2 of 7 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use Consistency Scene to generate a scene from a reference image, then preview or save the resulting image.
The graph includes image loading, reference preprocessing, ControlNet and IP-Adapter processing, prompt encoding, sampling, VAE decoding, preview, and saving.
LoadImage is the named image input, while PreviewImage and SaveImage are the named nodes for viewing and saving the generated image.
Slavikson published the workflow, and it lists Illustrious as its base model.
The workflow lists these model files: AnytestV4.safetensors, CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors, controlnet_depth_sdxl.safetensors, divingIllustriousFlat_v40VAE.safetensors, noob-sdxl-controlnet-lineart_anime.fp16.safetensors, noobaiXLControlnet_epsCanny.safetensors,
It also lists noobIPAMARK1_mark1.safetensors, plus these node packs: comfyui_controlnet_aux, comfyui_essentials, comfyui_ipadapter_plus, ComfyUI_JPS-Nodes, comfyui-advanced-controlnet, comfyui-custom-scripts, comfyui-easy-use, comfyui-impact-pack, comfyui-kjnodes, comfyui-rmbg,
For adaptation, review the prompt, seed, and image-size controls; the graph includes CLIPTextEncode, Seed (rgthree), and SDXLEmptyLatentSizePicker+.
Suggestion · not verified
The creator describes the workflow as very simplistic with few features and says they have not experimented much with scenes.
Before using it, verify that the listed model files and node packs are available in your setup.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 268 downloads · Type Workflows · Base model Illustrious
Requirements
19 requirementsControlNet · 2.33 GB · SAFETENSORS · fp16 · full · Unknown
CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
Not resolvedVision model · Unknown
controlnet_depth_sdxl.safetensors
Not resolvedControlNet · Unknown
divingIllustriousFlat_v40VAE.safetensors
Not resolvedVAE · Unknown
noob-sdxl-controlnet-lineart_anime.fp16.safetensors
Not resolvedControlNet · Unknown
ControlNet · 4.66 GB · SAFETENSORS · fp32 · full · Unknown
noobIPAMARK1_mark1.safetensors
Not resolvedCheckpoint · Unknown
comfyui_controlnet_aux
PossibleNode pack · Registry
Node pack · Registry
comfyui_ipadapter_plus
PossibleNode pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
was-node-suite-comfyui
PossibleNode pack · Registry