SDXL to Stable Cascade [ComfyUI]

Working with all previous Diffusion models; This workflow used Control Net and Lora's with SD1.5, SD2.1 & SDXL, then pushes them into Cascade img2img. While this only offers an approximation of what Cascade can produce, it does offer a stop gap bridging the models and allowing access to previously trained concept and styles.

00:00 Welcome
00:21 Introduction
02:30 v54 Discussion
07:30 v54 Walkthrough
21:07 v43 Walkthrough

- Workflow Packs:

- SDXL Lora's

- Introducing series (music/video)

- Checkpoint Merging

- cosXL / cosXL-edit conversion

- 3D Generation

- New Diffusion Models (April '24)
Stable Cascade:
SDXS-512:
cosXL & cosXL-edit:

- Stable Cascade series:

- Image Model Training

- Music with Audacity

- DJZ custom nodes (aspectsize node)

stable diffusion cascade
stable diffusion lora training
comfyui nodes explained
comfyui video generation
comfyui tutorial 2024
best comfyui workflows
comfyui image to image
comfyui checkpoints
civitai stable diffusion tutorial

[sprinteroptions]

Works here! I used the 1.5 flow, upscale didn't really matter. I was even able to get reactor to work too on m 4gb vram! Great work man! It's crazy to see the shift and how it'll fix text after the jump to cascade.. super cool man. great work. takes about 4min on a doodoo laptop w/ rtx 3050

[garrettdonahue]

Fantastic! I'm eagerly waiting for some video outputs.

[johndebattista-qe]

I hope my friend they can maybe do something with the reactor they can make it more easy to install it

[captainpike]

Thank you for great content, I have little critics, Can you make it your ComfyUI full screen it is hard to follow on Laptop, Secondly your avatar creates distraction, takes so much space on screen, I see other AI channels using some kind of robotic avatars non of them look good too just distraction. Thanks