Comments (4)
check this video out : https://youtu.be/-xEwaQ54DI4
also if you prefer i have auto installers for main and flux branch as well
from kohya_ss.
I have written an instruction for kohya_ss on RunPod at https://github.com/StableLlama/kohya_on_RunPod
The more people that try it and fix bugs the more people will benefit from it. So far I could already train my first Flux LoRA on a 48GB VRAM GPU :)
from kohya_ss.
I have written an instruction for kohya_ss on RunPod at https://github.com/StableLlama/kohya_on_RunPod
The more people that try it and fix bugs the more people will benefit from it. So far I could already train my first Flux LoRA on a 48GB VRAM GPU :)
Hello there, do you think it's would be possible to make a persistent template of the branch sd3-flux for runpod ?
from kohya_ss.
I don't know much about the RunPod templates but I know a bit about Docker containers.
It should be easy to bake it into a container.
But the Flux @ kohya code is currently developed at a very high pace so I think it's now worthwhile to make it fixed. We should wait until there's a release and then do it.
from kohya_ss.
Related Issues (20)
- Extract a Lora with specified Network Alpha for weight scaling (Question)
- Flux.dev - BF16 is set instead of FP16
- sd-scripts is checked out at the wrong commit HOT 1
- "stop training" button doesn't work properly, and the config file .json not storing the locations of the image folders
- Easier multires bucketing system like ai toolkit
- SDXL Dreambooth (not LoRA) NaN detected in latents HOT 7
- Discrepancies betw input args for UI vs CLI? HOT 4
- How " reshard " the 3 .safetensors file of a flux fine tuned checkpoint
- Finetuning No metadata error HOT 8
- Flux sampling taking 4-5 mins on wandb with 1024 training HOT 1
- Convolution Rank (Dimension) and Convolutoion Alpha for Flux disappear HOT 24
- After changing to SD3.flux branch - UnboundLocalError: local variable 'text_encoder_conds' referenced before assignment
- TypeError: Adafactor.__init__() got an unexpected keyword argument 'fused_backward_pass' HOT 2
- meta-lat.json and meta_cap.json for full finetuning mandatory ? HOT 1
- How include all folders for meta_cap.sjon and meta_lat.json
- Help Question - Permission set HOT 1
- SD3.Flux branch, fresh install: RuntimeError: use_libuv was requested but PyTorch was build without libuv support HOT 2
- multires training with toml seems to learn nothing HOT 1
- [MINOR] Glitch in latent caching stdout output
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kohya_ss.