My 2-stage (base + refiner) workflows for SDXL 1.0 in ComfyUI, with separate prompts for text encoders. If you don't need LoRA support, separate seeds, CLIP controls, or hires fix - you can just grab basic v1.0 workflow. Works with bare ComfyUI (no custom nodes needed).
SD+XL workflows are variants that can use previous generations SD models to provide initial scene concept.
Links to SDXL 1.0 model files:
sd_xl_base_1.0.safetensors or sd_xl_base_1.0_0.9vae.safetensors* (6.94 GB),
sd_xl_refiner_1.0.safetensors or sd_xl_refiner_1.0_0.9vae.safetensors* (6.08 GB),
sd_xl_offset_example-lora_1.0.safetensors (49.6 MB).
* versions with fixed issue #4310.
Link to ControlNet 1.1 model files (used in SD+XL v1.2):
Link to my SD 1.5 variant used in SD+XL workflow:
MoonRide Mix 10 (you can replace it with any other SD variant you like).
Parameters to play with:
text in prompts,
width and height (but stick to combinations used during SDXL training - listed in notes section),
noise seeds,
steps ("end_at_step" is switching point between base and refiner - should be about 50% to 95% of total steps, depending on selected scheduler and samplers - look at preview image from base to check what is being passed to refiner stage),
scheduler,
sampler names,
cfg (lower - more creative, but also less defined),
CLIP Skip (-1 will treat prompts more literally, -3 will generalise),
LoRA strengths (0 means disabled).
Cheers, and have fun!
Description
Changes since SD+XL v1.0:
added img2img hires fix (using SDXL refiner).
FAQ
Comments (8)
Where is seed set in the latest version?
Noise seed parameter in samplers - you can do it separately for each one of them. Biggest impact is in the base, but you might want to check out different values in refiner or hires refiner, too.
Hello! Dear author, how to run a real photo through your circuit? Thank you.
You'd need to replace empty latent with loaded image, then upscale it to total pixels 1 MP, VAE encode it, and also increase starting step a bit (depending on how much denoising you want).
You can take a look at SD+XL v1.0 workflow, where output from SD model in taken as input to further processing via SDXL.
@MoonRide Thanks for the answer, but I can't change the scheme for a real photo, I'm just learning.
@MoonRide Not to be that guy but what did you mean by increase starting step? Just want to be sure what you ment.
So Thankful one of these workflows FINALLY works... I have gone through about 8 of these now just trying to get started in ComfyUI and so many of these have models and nodes that are either deprecated or not in the Manager. So Thank YOU!!!
Thank you so much for your worklow!