Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
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...
Profil d'exécution
Description de la source
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.
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.
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.
Suggestion · non vérifié
Verify that the listed workflow components are available in your setup before use; no source URLs are provided for them.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource 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.
Estimation des besoins VRAM
Estimation indisponible
63,9 MB sur 1 de 8 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 50Upscaler · 63.9 MB · PTH · Unknown
ImageUpscaleWithModel
Non résoluUpscaler · Unknown
longclip-L.pt
Non résoluText encoder · Unknown
sdxl_lustify_endgame.safetensors
Non résoluCheckpoint · Unknown
sdxl_tile_realistic_v2_fp16.safetensors
Non résoluControlNet · Unknown
UpscaleModelLoader
Non résoluUpscaler · Unknown
VAEDecode
Non résoluVAE · Unknown
VAEEncode
Non résoluVAE · Unknown
ACN_AdvancedControlNetApply_v2
Non résoluPack de nœud · Unknown
ACN_ScaledSoftControlNetWeights
Non résoluPack de nœud · Unknown
ACN_TimestepKeyframeInterpolation
Non résoluPack de nœud · Unknown
Pack de nœud · Unknown
Anything Everywhere
Non résoluPack de nœud · Unknown
Anything Everywhere3
Non résoluPack de nœud · Unknown
ApplyFBCacheOnModel
Non résoluPack de nœud · Unknown
BasicGuider
Non résoluPack de nœud · Unknown
BasicScheduler
Non résoluPack de nœud · Unknown
CheckpointLoaderSimple
Non résoluPack de nœud · Unknown
CLIPTextEncodeBREAK
Non résoluPack de nœud · Unknown
ControlNetLoader
Non résoluPack de nœud · Unknown
DetailDaemonSamplerNode
Non résoluPack de nœud · Unknown
DynSamplerSelect
Non résoluPack de nœud · Unknown
easy imageBatchToImageList
Non résoluPack de nœud · Unknown
easy imageListToImageBatch
Non résoluPack de nœud · Unknown
Empty Latent by Pixels (WLSH)
Non résoluPack de nœud · Unknown
Fast Groups Muter (rgthree)
Non résoluPack de nœud · Unknown
GetNode
Non résoluPack de nœud · Unknown
Image Comparer (rgthree)
Non résoluPack de nœud · Unknown
Image Save
Non résoluPack de nœud · Unknown
ImageScaleToTotalPixels
Non résoluPack de nœud · Unknown
JoinStrings
Non résoluPack de nœud · Unknown
KSamplerSelect
Non résoluPack de nœud · Unknown
LayerMask: LoadFlorence2Model
Non résoluPack de nœud · Unknown
LayerUtility: Florence2Image2Prompt
Non résoluPack de nœud · Unknown
MarkdownNote
Non résoluPack de nœud · Unknown
PerturbedAttention
Non résoluPack de nœud · Unknown
Power Lora Loader (rgthree)
Non résoluPack de nœud · Unknown
PreviewImage
Non résoluPack de nœud · Unknown
RandomNoise
Non résoluPack de nœud · Unknown
SamplerCustomAdvanced
Non résoluPack de nœud · Unknown
ScheduledPerpNegCFGGuider //Inspire
Non résoluPack de nœud · Unknown
SeaArtLongXLClipMerge
Non résoluPack de nœud · Unknown
Seed Everywhere
Non résoluPack de nœud · Unknown
SetNode
Non résoluPack de nœud · Unknown
ShowText|pysssss
Non résoluPack de nœud · Unknown
Text Multiline
Non résoluPack de nœud · Unknown
TiledDiffusion
Non résoluPack de nœud · Unknown
TTP_Image_Assy
Non résoluPack de nœud · Unknown
TTP_Image_Tile_Batch
Non résoluPack de nœud · Unknown
TTP_Tile_image_size
Non résoluPack de nœud · Unknown
