Comments (4)
As a second step I trained a model with a new dataset based on the example script. It was very straightforward 🔥 and everything worked together very nicely, except for my GPU not allowing larger models, so I had to decrease resolution. I would have loved a push_to_hub
method to upload it
from diffusers.
Thanks a lot for the feedback !
I1. (first code example):
- Yes,
diffusers
tag would be awesome. - Yes, we could definitely add code snippet once the API is finalised.
I2 (first code example):
The example is failing because of renaming. GaussianDDPMScheduler
is now DDPMScheduler
. These will be fixed once we settle on names. Fixed this example for now :)
This also makes me wonder what's the difference between just using the diffusion pipeline directly as in the model card vs using DDPMScheduler + UNetModel approach as in the README. Is the pipeline approach just a wrapper of both?
We are aiming for two APIs here:
press a button
API with pipeline, where user could just load the pipeline and use it as it is for inference. This is more abstract and black-box API to play with pre-trained pipelines.barebone/follow-the-equation
: Which offers more control , allows to mix and match different schedulers and models, write your own denoising loop. This is close to how these models are presented in research papers.
I3 (second code example)
Should num_inference_steps be len(noise_scheduler) as in first example?
some schedulers like DDIM allows you to use different num_inference_steps
than what was used during the training to allow fast inference. So this is intended, num_inference_steps
and len(noise_scheduler)
can be different.
I4 and I6:
The models were added in a fast hacky way to get the initial version rolling. All of these will improved before formal release.
I would have loved a push_to_hub method to upload it
@anton-l is already working on it :)
from diffusers.
I1
- Happy to help with setting up the code snippet + tag once the API is finalised.
I2
- Thanks!
I3
- Cool, then this is analogous to
*Model
classes andpipeline
intransformers
. Sounds exciting!
For push to Hub, feel free me to tag me in the PR once opened, it would be cool to have metrics and other metadata out-of-the-box
from diffusers.
Thanks for the feedback here @osanseviero - think we applied almost all of it now :-)
from diffusers.
Related Issues (20)
- About training controlnet with lora and meet problems
- support Kandinsky 3.1
- `StableDiffusionXLControlNetInpaintPipeline` not working with IP-Adapter when using `ip_adapter_image_embeds` parameter. HOT 1
- stabilityai/stable-diffusion-2-1 does not appear to have a file named config.json. HOT 3
- Load local safetensors file raised invalid json format HOT 3
- fail to load modal from same folder HOT 2
- [ko] Translating docs(Conceptual Guides) to Korean. HOT 3
- Combining community pipeline for image generation HOT 3
- custom_pipeline not being cached
- Support MuLan, a plug-and-play language adapter to adapt existing diffusion model for up to 110+ languages without additional training
- PyTorch 2.3.0 Incompatibility with Current Diffusers Library HOT 5
- Add support for custom CLIPTextModelWithProjection in SDXL for new language training
- how can i know what the model base are HOT 2
- ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preservation
- How to implement `IPAdapterAttnProcessor2_0` with xformers
- [training examples] reduce complexity by running final validations before export
- SDXL Training Fails for Multi GPU Machine HOT 6
- Instruct-pix2pix pipeline: add ability to pass `cross_attention_kwargs` in call method HOT 2
- Attention in Motion Module of UNetMotionModel HOT 1
- Increasing RAM usage with enable_model_cpu_offload HOT 6
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 diffusers.