¿Tienes un flujo de trabajo de ComfyUI? Obtén un Workflow Doc legible en tu navegador.Haz legible un flujo de trabajo.Pruébalo ahora ↗
This is my "Ultimate" SDXL workflow. After about a year of messing around with SDXL checkpoints. This is what i've sort of landed with that has a good balance of quality and speed. 3 minutes from 0 to 2721x6167 that...
Perfil de ejecución
Descripción de la fuente
Intro
This is my "Ultimate" SDXL workflow. After about a year of messing around with SDXL checkpoints. This is what i've sort of landed with that has a good balance of quality and speed. 3 minutes from 0 to 2721x6167 that blows the doors off Flux. It tries to push SDXL to the max in terms of detail and resolution trying to match FLUX. Tons of great SDXL models that I wish had the clean Flux look. You can make stuff that looks VERY close to Flux by using alot of these great extentions that in my opinion put SDXL on Meth. Some of this stuff is very obscure and most workflows are overly bloated with nonsense. Hopefully this is something that you can just expand on as a base.
QuickStart
Everything is initially setup for pure text-to-image. Enter a prompt and hit queue. Example prompt is provided.
Comentario generado por IA
Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.
SDXL Ultimate 16 MegaPixel is an SDXL workflow for generating images from text prompts, refining source images through image-to-image or depth-controlnet guidance, and upscaling results through tiled stages toward 8MP and 16MP outputs.
The default path is pure text-to-image: enter a prompt and queue it. Enable the image-to-image or depth-controlnet group for those paths.
The notes describe composition and cleanup around 2MP before tiled refinement at 8MP and 16MP.
Inputs are text prompts, source images for image-to-image, and optional depth-controlnet guidance.
The workflow covers text-to-image, image-to-image, and upscaling, with stages described at 2MP, 8MP, and 16MP.
It uses SDXL 1.0 as its base model and is published by Smeks.
Named model files are 4x_foolhardy_Remacri.pth, longclip-L.pt, sdxl_lustify_endgame.safetensors, and sdxl_tile_realistic_v2_fp16.safetensors.
Named workflow components include ACN_AdvancedControlNetApply_v2, ACN_ScaledSoftControlNetWeights, ACN_TimestepKeyframeInterpolation, Any Switch (rgthree), Anything Everywhere, Anything Everywhere3, ApplyFBCacheOnModel, BasicGuider, BasicScheduler, CheckpointLoaderSimple, CLIPTÉ
Other named workflow components include CLIPTextEncodeBREAK, ControlNetLoader, DetailDaemonSamplerNode, DynSamplerSelect, easy imageBatchToImageList, easy imageListToImageBatch, Empty Latent by Pixels (WLSH), Fast Groups Muter (rgthree), GetNode, Image Comparer (rgthree), Image
SeaArtLongXLClipMerge is described as extending CLIP handling from 77 to 248 tokens.
Conditional merges are entered in one prompt with BREAK separators; the notes describe PerturbedAttention settings of 1.5–2.
For the 8MP and 16MP stages, the notes specify 30% denoise for defogging and sharpening.
Before use, verify that 4x_foolhardy_Remacri.pth, longclip-L.pt, sdxl_lustify_endgame.safetensors, and sdxl_tile_realistic_v2_fp16.safetensors are available; no source URL is provided for them.
Sugerencia · sin verificar
Verify that the listed workflow components are available in your setup before use; no source URLs are provided for them.
Sugerencia · sin verificar
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuenteExtractos de fuentes
1 extractoSource context: 703 downloads · Type Workflows · Base model SDXL 1.0
Optional Stuff
Everything is setup to do depth-controlnet or image-to-image without messing with anything. Just enable the following group and go.
image-to-image
depth-controlnet
Advanced
There are many knobs to tweak. Honestly, you'll have to experiment and see what does what, but breifely I think its worth at least noting from my experience most important bits.
SeaArtLongXLClipMerge All SD checkpoints have a clip limited to 77 tokens and so this patches any clip to 248 tokens allowing alot more detailes. Actual human readable prompts work with it much better similar to flux but it's still very limited. Each tile can hold 248 tokens generated from Florence + base prompt which gives unbelevable results at high tile counts.
Clip Text Encode with BREAK This in conjuction with the long clip merge node gives alot of new possibilities and simplifies a ton of noodles around conditioning. Conditional merges are all in one prompt seperated by the BREAK.
CLIP NegPip + PerturbedAttentionGuidance This definetly helps cleanup the image alot. Generations are much more coherent and make sense. Alot of artifacting goes away by simply having these enabled. A setting of 1.5-2 is about all you really want.
Dynamic Sampler + Detail Daemon I have all this setup how i want but you may want to experiment, but these dynamic samplers push alot more refined + smooth details out of the image almost like flux. Honestly you dont even need to pass the image through Flux because it looks that clean.
Conclusion
Basically steps 1 and 2 are the primers for the actual tiling steps 3 and 4. The image has to be nearly perfect in composition and mostly free from any major artifacting before going into tiling. Step 1 tries to just get a good composition and you may have to change around conditioning and CFG ramping to get a desired result depending on model used etc. Step 2 does the heavy lifting to clean up everything and 2 Mega Pixels seems to be the sweet spot with the TTPlanet Realistic Tile Controlnet before requiring full breakup into tiles. Step 3 and 4 require a nearly perfect image for them to work properly. Going to 8MP and 16MP only requires 30% denoise for "defogging" and "sharpening" everything to bring it all into focus. After 2MP the need for CFG and denoise goes away as you already have the image. It's really just a matter of massaging defects out along the way to 16MP. Thats just my perspective on it all.
Curious to see what people think and would wanna see anything that could improve on this because ive tried so many workflows in the past and nothing ever seemed to really go as far as this.
Requisito de VRAM estimado
Estimación no disponible
63,9 MB en 1 de 8 archivos de modelos. Total de archivos de modelos + 25 % de sobrecarga de carga + 2 GB de margen de ejecución, redondeado hacia arriba.
Requisitos
50 requisitosUpscaler · 63.9 MB · PTH · Unknown
ImageUpscaleWithModel
No resueltoUpscaler · Unknown
longclip-L.pt
No resueltoText encoder · Unknown
sdxl_lustify_endgame.safetensors
No resueltoCheckpoint · Unknown
sdxl_tile_realistic_v2_fp16.safetensors
No resueltoControlNet · Unknown
UpscaleModelLoader
No resueltoUpscaler · Unknown
VAEDecode
No resueltoVAE · Unknown
VAEEncode
No resueltoVAE · Unknown
ACN_AdvancedControlNetApply_v2
No resueltoPaquete de nodos · Unknown
ACN_ScaledSoftControlNetWeights
No resueltoPaquete de nodos · Unknown
ACN_TimestepKeyframeInterpolation
No resueltoPaquete de nodos · Unknown
Any Switch (rgthree)
Paquete de nodos · Unknown
Anything Everywhere
No resueltoPaquete de nodos · Unknown
Anything Everywhere3
No resueltoPaquete de nodos · Unknown
ApplyFBCacheOnModel
No resueltoPaquete de nodos · Unknown
BasicGuider
No resueltoPaquete de nodos · Unknown
BasicScheduler
No resueltoPaquete de nodos · Unknown
CheckpointLoaderSimple
No resueltoPaquete de nodos · Unknown
CLIPTextEncodeBREAK
No resueltoPaquete de nodos · Unknown
ControlNetLoader
No resueltoPaquete de nodos · Unknown
DetailDaemonSamplerNode
No resueltoPaquete de nodos · Unknown
DynSamplerSelect
No resueltoPaquete de nodos · Unknown
easy imageBatchToImageList
No resueltoPaquete de nodos · Unknown
easy imageListToImageBatch
No resueltoPaquete de nodos · Unknown
Empty Latent by Pixels (WLSH)
No resueltoPaquete de nodos · Unknown
Fast Groups Muter (rgthree)
No resueltoPaquete de nodos · Unknown
GetNode
No resueltoPaquete de nodos · Unknown
Image Comparer (rgthree)
No resueltoPaquete de nodos · Unknown
Image Save
No resueltoPaquete de nodos · Unknown
ImageScaleToTotalPixels
No resueltoPaquete de nodos · Unknown
JoinStrings
No resueltoPaquete de nodos · Unknown
KSamplerSelect
No resueltoPaquete de nodos · Unknown
LayerMask: LoadFlorence2Model
No resueltoPaquete de nodos · Unknown
LayerUtility: Florence2Image2Prompt
No resueltoPaquete de nodos · Unknown
MarkdownNote
No resueltoPaquete de nodos · Unknown
PerturbedAttention
No resueltoPaquete de nodos · Unknown
Power Lora Loader (rgthree)
No resueltoPaquete de nodos · Unknown
PreviewImage
No resueltoPaquete de nodos · Unknown
RandomNoise
No resueltoPaquete de nodos · Unknown
SamplerCustomAdvanced
No resueltoPaquete de nodos · Unknown
ScheduledPerpNegCFGGuider //Inspire
No resueltoPaquete de nodos · Unknown
SeaArtLongXLClipMerge
No resueltoPaquete de nodos · Unknown
Seed Everywhere
No resueltoPaquete de nodos · Unknown
SetNode
No resueltoPaquete de nodos · Unknown
ShowText|pysssss
No resueltoPaquete de nodos · Unknown
Text Multiline
No resueltoPaquete de nodos · Unknown
TiledDiffusion
No resueltoPaquete de nodos · Unknown
TTP_Image_Assy
No resueltoPaquete de nodos · Unknown
TTP_Image_Tile_Batch
No resueltoPaquete de nodos · Unknown
TTP_Tile_image_size
No resueltoPaquete de nodos · Unknown
