Chris Green
banner
chrisukgreen.bsky.social
Chris Green
@chrisukgreen.bsky.social
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.

https://substack.com/@chrisukgreen
New substack post taking a look at some of the current video diffusion models available in ComfyUI and online

diffusiondoodles.substack.com/p/big-steps-...

#ai #comfyui #video #imagegeneration
May 16, 2025 at 8:59 AM
HiDream-I1 isn't perfect and can fail in similar ways to Flux. Its prompt adherence is strong. Images look different to Flux but hard to say what is different! Created with no LoRAs or refined models. HiDream-I1 (Q8 GGUF), multi-stage sampling & Ultimate SD.
#GenAI #diffusionmodels #comfyUI #hidream
May 1, 2025 at 8:57 PM
Experimenting with the Q8 quantised version of Hi-Dream. Performance/quality trade-off is good.

#GenAI #diffusionmodels #imagegeneration #comfyUI #hidream
May 1, 2025 at 12:31 PM
This week's post on the Diffusion Doodles Substack (diffusiondoodles.substack.com/p/how-to-tra...) looks at creating your own LoRAs for consistent styles and characters.

#GenAI #diffusionmodels #imagegeneration #comfyUI #flux #loras #characterdesign
April 23, 2025 at 9:56 AM
Trying Fluxmania V with a simple portrait. Which do you prefer - black & white or muted Colour? #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #portrait
April 15, 2025 at 5:56 PM
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
April 14, 2025 at 2:49 PM
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
April 12, 2025 at 12:56 PM
Festival of Colours - Flux Dev with Defluxion II LoRA and FaceDetailer using Tenofas' Modular Workflow. #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #color #spring
April 10, 2025 at 6:45 AM
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
April 8, 2025 at 11:26 AM
Second of today's anime doodles, again created using Flux Dev and Anime Art v3 LoRA with a controlnet and prompt. #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #anime
April 7, 2025 at 8:12 PM
Doodling with some anime images using Flux Dev and Anime Art v3 LoRA with a controlnet and prompt. #GenAI #diffusionmodels #imagegeneration #comfyUI #flux
April 7, 2025 at 12:58 PM
Alternative version of the image posted yesterday, uses the same source images but with the Flux IP Adapter rather than IP Adapter Plus which used SDXL. #GenAI #diffusionmodels #imagegeneration #comfyUI #flux #stablediffusion
April 4, 2025 at 10:35 AM
A new post over at diffusiondoodles.substack.com/p/comfyui-be... about moving beyond text prompts into image-to-image generation methods. Aimed at the newbie rather than the seasoned pro, so ideal if you are just finding your way with ComfyUI.
#GenAI #diffusionmodels #imagegeneration #comfyUI #flux
April 3, 2025 at 9:22 PM
Experimenting with IPAdapters and ControlNets to change the style of some recent photos from Istanbul #GenAI #diffusionmodels #dailydoodle #imagegeneration #comfyUI #flux #fluxai #topkapı
diffusiondoodles.substack.com
April 1, 2025 at 11:58 AM
Sunset Couple Variations - first two images are the same base model each with a different LoRA. Third image is a refined model with the same LoRA as the first image, all with the same prompt & controlnet #GenAI #diffusionmodels #dailydoodle #imagegen #comfyUI #flux
diffusiondoodles.substack.com
March 27, 2025 at 4:13 PM
Something a little abstract (and a bit dark) for a Tuesday - visual interpretation of the Doomsday Clock and its current time. #GenAI #diffusionmodels #dailydoodle #imagegeneration #comfyUI #flux #fluxai
diffusiondoodles.substack.com
March 25, 2025 at 9:29 AM
Trying some different models & created this slightly weird doodle - somewhere between an art installation and a theatre stage effect. Can’t decide whether I like it or not - started very differently and evolved! #GenAI #diffusionmodels #dailydoodle #comfyUI #flux
diffusiondoodles.substack.com
March 21, 2025 at 11:30 AM
Something simple, yet moody that came out of some model testing today and messing about creating a lighting effect. #GenAI #diffusionmodels #dailydoodle #imagegeneration #comfyUI #flux #fluxai
diffusiondoodles.substack.com
March 20, 2025 at 10:02 PM
Just published a new article on Substack aimed at beginners in the world of AI image generation focussing on LoRAs (Low-Rank Adaptation models)
diffusiondoodles.substack.com/p/world-of-l...
#GenAI #diffusionmodels #imagegeneration #comfyUI #flux #fluxai
March 19, 2025 at 2:33 PM
An attempt at a nostalgic 1960s photograph . This is based on Colossus Project Flux v5 with multi-stage sampling, no LoRAs and CannyEdge Pre-processing. #nostalgia #younglove #GenAI #diffusionmodels #dailydoodle #imagegeneration #comfyUI #flux #fluxai
diffusiondoodles.substack.com
March 17, 2025 at 10:44 PM
Friday doodle - imaginary battle-scarred dinosaur. Created with Flux.1 Dev & Tenofas WF v5, with Anti-Blur, Aidma Hyper Realism v0.3 and Hyper Flux.1 Dev 16 Step LoRAs, euler/beta + detailer demon and FG of 2.0 #GenAI #diffusionmodels #dailydoodle #comfyUI #flux diffusiondoodles.substack.com
March 14, 2025 at 2:46 PM
Going vintage for today's diffusion doodle - an attempt at a 'restored' sepia photograph. Created using Colossus Project Flux v5 with no Loras, multi-stage sampling and flux guidance of 2.2 #GenAI #diffusionmodels #dailydoodle #imagegeneration #comfyUI #flux #fluxai

diffusiondoodles.substack.com
March 13, 2025 at 4:37 PM
March 10, 2025 at 10:27 PM