Activity
Mon
Wed
Fri
Sun
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
What is this?
Less
More

Memberships

The Weavy Way™ | Master Nodes

155 members • Free

The Synthetic Way Creative AI

11 members • Free

4 contributions to The Weavy Way™ | Master Nodes
Extracting/Up-scaling single images for a 3x3 storyboard.
The aim here is to stress-test weavy to extract a single image from a storyboard whilst keeping all details exactly the same as they appear in the the smaller grid images. I have played around with using image upscales such as Topaz with limited success. The AI seems to hallucinate and fill in details such as decals on the bike and also the bike itself. After many conversations with LLMs- in case Claude it appears that the best solution is to independently create 9 single high res images. Weavy does not like trying to extract 1 single image from a grid in one sweep- it gets confused and the details are muddled at best. I'm putting this in the community to see if anyone else has come across this issue and their workflows to resolve this.
Extracting/Up-scaling single images for a 3x3 storyboard.
1 like • 9d
I prompt it to create 9 cinematic stills in a 3x3 grid. Within that prompt I have 9 detailed descriptions of what each frame should contain.
1 like • 9d
having some success using the crop tool within weavy will do some more testing and report back.
JSON prompts are overrated. (Or am I missing something?)
Someone asked me this week what I think about JSON-structured prompts inside nodes. Honest answer: I don't really use them (now). Every time I look at a 40-line JSON block inside a prompt node I think there has to be a better way. It feels like writing a legal contract when all I want is a moody photograph. Plain language just flows better for me. Faster to write, easier to tweak mid-workflow. That said, maybe I'm using them wrong. Maybe there's a use case where JSON inside a node actually clicks and I'm just not seeing it. So tell me — do you use them? And if yes, for what? 👇 Vote below
Poll
11 members have voted
JSON prompts are overrated. (Or am I missing something?)
1 like • 14d
Have used JSON prompts before but the LLMs appear to process natural language better
Getting to grips with Weavy. Generating character sheets and locking in consistency
Need some help getting going with Weavy. I have generated some previous images in NBP and I like the model but would like to change the clothes to specific pieces and generate strong character sheets which I can then use to generate some cinematic stills from and eventually some moving images. The emphasis is on the neck snood as it is the product being 'advertised' Essentially I want to be able to produce a workflow which I can control each item of clothing. I have Also included a cinematic moodboard which I have previously created in NBP with the correct clothing
Getting to grips with Weavy. Generating character sheets and locking in consistency
0 likes • Feb 11
Ive had to put It on hold for the moment- as im working on another pitch. Hope to get going on it again soon!
0 likes • 16d
@Jamy Vodegel nope nothing- went completely cold unfortunately.
What should I build next? 🚀
Now that the school is getting up to speed and the basic classroom outline is ready, I want to make sure the next content drops are exactly what you need. Let me know in the comments! 👇 I’m reading everything. If you have a specific node or workflow in mind that’s giving you trouble, drop it below so I can prioritize it for the Classroom!
Poll
25 members have voted
What should I build next? 🚀
1 like • Feb 5
May be more interesting with a real brand as you can extract the aesthetic used by said brand and show how AI can then re-create it from the ground up
2 likes • Feb 5
I would push it back on them and ask what their inspirations are. Ie other brands, aesthetics that they like and then build it up from that. Brands always have a starting point- your aim should be to expand that and show them what's possible
1-4 of 4
D Ciufo
2
6points to level up
@daniel-ciufo-4589
ai studio

Active 3d ago
Joined Feb 3, 2026