Comments (4)
Shouldn't they be multiples of 8?
504x520 is a valid dimension in other SD pipelines.
The sd diffusion process run in the latent space of 1/8 of the width and height. In addition, unet will downsample the middle layer to 1/8 during the operation, so in fact the middle layer size will be 1/64 of width and height, which is why sd.cpp requires width and height to be multiples of 64.
If "sd" were to scale the latent space to a multiple of 8 before U-Net computation and then restore it to its original size afterward, it would indeed allow input widths and heights to be multiples of 8. However, I have not implemented it yet.
from stable-diffusion.cpp.
The height and width should be multiples of 64. I have updated the prompt for the command line parameters
from stable-diffusion.cpp.
The height and width should be multiples of 64. I have updated the prompt for the command line parameters
Nice workπ
from stable-diffusion.cpp.
Shouldn't they be multiples of 8?
504x520 is a valid dimension in other SD pipelines.
from stable-diffusion.cpp.
Related Issues (20)
- Could you add DirectML version of S-D.cpp, please? HOT 1
- SDXL-Lightning support HOT 12
- [Question] Can I convert a sd model with lora converting and merging into it?
- StableDiffusionGGML buffer problem : call txt2img twice HOT 2
- SDXL : LoRa problem HOT 17
- App crashes silently since the last update when loading a new model. HOT 2
- photoMaker issue with two or more generated images / SDXL sample steps HOT 12
- Errors during variational encoder step
- Are lora's for SDXL text encoder supported? HOT 7
- api not match with ggml updated version HOT 1
- Stable-diffusion on macOS M1 - GPU HOT 1
- doesn't work properly on Xiaomi 14 HOT 6
- Image generation error on M1 and low image quanlity HOT 2
- taesd model does not work after reloading the sd_ctx HOT 2
- ggml_metal_graph_compute_block_invoke: error: unsupported op 'MUL_MAT' (macos intel/amd gpu) HOT 1
- any plan to merge upstream libggml? HOT 2
- export some api to free the image memory HOT 1
- A few questions regarding Photomaker HOT 1
- report a bug instead of crash when vae_decoder_only=True and using img2img HOT 2
- txt2img can not be called multiple times. HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stable-diffusion.cpp.