dalle-flow
meadowrun
dalle-flow | meadowrun | |
---|---|---|
31 | 2 | |
2,823 | 93 | |
0.0% | - | |
2.3 | 9.1 | |
12 months ago | 10 months ago | |
Python | Python | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
dalle-flow
-
How to Personalize Stable Diffusion for ALL the Things
Jina AI is really into generative AI. It started out with DALLĀ·E Flow, swiftly followed by DiscoArt. And thenā¦š¦š¦*š¦š¦. At least for a whileā¦
-
image generation API similar to Dall-E or Dall-E 2
you can host your own https://github.com/jina-ai/dalle-flow
-
[hlkyās/sd-webui] Announcing Sygil.dev & Project Nataili
For example for all the multimodal stuff like clipseg and upscalers, I'm using isolated executors through jina flow: https://github.com/jina-ai/dalle-flow/tree/main/executors
-
Who needs prompt2prompt anyway? SD 1.5 inpainting model with clipseg prompt for "hair" and various prompts for different hair colors
clipseg is an image segmentation method used to find a mask for an image from a prompt. I implemented it as an executor for dalle-flow and added it to my bot yasd-discord-bot.
-
Sequential token weighting invented by Birch-san@Github allows you to bypass the 77 token limit and use any amount of tokens you want, also allows you to sequentially alter an image
Merged into [dalle-flow](https://github.com/jina-ai/dalle-flow/pull/112) this morning and works on my Discord bot [yasd-discord-bot](https://github.com/AmericanPresidentJimmyCarter/yasd-discord-bot).
-
I made a discord bot for artsy ML stuff - just finished integrating SD
https://github.com/jina-ai/dalle-flow with ports of some code from https://github.com/lstein/stable-diffusion plus some stuff specific to my uses (mostly more exposed settings and meta data on the outputs).
-
AI generated picture "Beatles at Disneyland"
dalle flow - a more advanced version of dall-e mini, running dall-e mega and a diffusion model (free colab), free
- Comparison of DALL-E, Midjourney, Stable Diffusion and more
-
Running Dall-e mini on Windows? (Or: Are there any equivalent text-to-image AI's I can run on a windows PC with a 2080 TI?)
Another option is https://github.com/jina-ai/dalle-flow combines DALL-E Mini with some other image processing models, and they have a pre-built Docker image that you could run locally. However, because it loads additional image processing models, you'll need about 21 GB of GPU RAM which is more than a 2080 TI has. You could always try to edit their Dockerfile and re-build it to remove the other models.
-
Run Your Own DALLĀ·E Mini (Craiyon) Server on EC2
For the second half of this article, weāll use meadowdata/meadowrun-dallemini-demo which contains a notebook for running multiple models as sequential batch jobs to generate images using Meadowrun. The combination of models is inspired by jina-ai/dalle-flow.
meadowrun
-
Run Your Own DALLĀ·E Mini (Craiyon) Server on EC2
If youāre anything like us, though, youāll feel compelled to poke around the code and run the model yourself. Weāll do that in this article using Meadowrun, an open-source library that makes it easy to run Python code in the cloud. For ML models in particular, we just added a feature for requesting GPU machines in a recent release. Weāll also feed the images generated by DALLĀ·E Mini into additional image processing models (GLID-3-xl and SwinIR) to improve the quality of our generated images. Along the way weāll deal with the speedbumps that come up when running open-source ML models on EC2.
-
Why Starting Python on a Fresh EC2 Instance Takes Over a Minute
So it is more reasonable to cache the download locally for up to 4 hours. That saves us 5ā10 seconds on every run.
What are some alternatives?
dalle-mini - DALLĀ·E Mini - Generate images from a text prompt
dalle-playground - A playground to generate images from any text prompt using Stable Diffusion (past: using DALL-E Mini)
jina - āļø Build multimodal AI applications with cloud-native stack
glid-3-xl - 1.4B latent diffusion model fine tuning
BasicSR - Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
warehouse - The Python Package Index
example-app-store - App store search example, using Jina as backend and Streamlit as frontend
glid-3-xl - 1.4B latent diffusion model fine tuning
jax - Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
dalle2-in-python - Use DALLĀ·E 2 in Python
distribution - Placeholder repository to allow filing of general bugs/issues/etc against the Clear Linux OS for Intel Architecture linux distribution