Chris Green

@chrisukgreen
1 Followers
3 Following
28 Posts
Fractional COO and CTO in the daytime. Co-founder & MD of Etherlive for many years delivering technology to live events. Lifelong tech enthusiast, hobbyist GenAI and long term music DAW user. Images on this feed are AI Generated, the words are human!
Substackhttps://substack.com/@chrisukgreen

New substack post taking a look at some of the current video diffusion models available in ComfyUI and online

https://diffusiondoodles.substack.com/p/big-steps-forward-in-video-generation

#ai #comfyui #video #imagegeneration

Big Steps Forward in Video Generation

Video diffusion models are stepping up to change video creation

Diffusion Doodles

My second article in 'Notes from a Small Business' reflects on reasons for starting a business, motivation, character traits, founder age and the importance of understanding the journey, not just the end goal.

https://notesfromasmallbusiness.substack.com/p/why-would-you-start-a-business

Why Would You Start a Business?

Reflections from a Founder

Notes from a Small Business

HiDream-I1 isn't perfect and occasionally fails in similar ways to Flux but its prompt adherence is strong. The images just look different to Flux but hard to say what is different!

This image was created with no LoRAs or refined models, just straight up HiDream-I1 (Q8 GGUF) with multi-stage sampling and Ultimate SD Upscale.

#GenAI #diffusionmodels #imagegeneration #comfyUI #hidream

Experimenting with the Q8 quantised version of Hi-Dream. Performance/quality trade-off is good.

#GenAI #diffusionmodels #imagegeneration #comfyUI #hidream

This week's post on the Diffusion Doodles Substack (https://diffusiondoodles.substack.com/p/how-to-train-a-lora) looks at creating your own LoRAs for consistent styles and characters.

#GenAI #diffusionmodels #imagegeneration #comfyUI #flux #loras #characterdesign

How to Train a LoRA

The Best Solution for Consistent Styles & Characters

Diffusion Doodles
Trying Fluxmania V with a simple portrait. Which do you prefer - black & white or muted Colour? #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #portrait
Experimenting with consistent character generation using a LoRA trained from images created using a character sheet workflow #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #anime #characterdesign #characterillustration
Retro 1930s film star B&W image with split toning. Flux Dev with Defluxion II & AntiBlur LoRAs with a FaceDetailer #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #bandw #retro #splittone
Festival of Colours - Flux Dev with Defluxion II LoRA and FaceDetailer using Tenofas' Modular Workflow. #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #color #spring
Sunflowers at Sunrise - A nice nature picture for a sunny spring morning. Flux Dev with Defluxion II and AntiBlur LoRAs using Tenofas' Modular Workflow. #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #nature #bees