Evanw wu
012ywu
AI & ML interests
None yet
Recent Activity
reacted to salma-remyx's post with 🔥 26 minutes ago
We just published two training-free 🧩 Modular Diffusers community pipelines that push off-the-shelf FLUX to 4096².
No fine-tuning, no extra weights, no upscaler.
The methods take different routes around positional extrapolation:
âś… **HRDiT:** resolution ladder + NTK RoPE + spatial-position alignment + structure guidance
✅ **DyPE:** single-pass, timestep-dynamic RoPE (κ=t²), plus an optional SEGA spectral mode that removes high-frequency speckle
Because both expose the same block interface, you can A/B the two methods on the same FLUX.1-Krea-dev weights by swapping the repo ID:
```python
import torch
from diffusers import ModularPipeline
repo_id = "remyxai/dype-flux-modular"
# or "remyxai/hrdit-flux-modular"
pipe = ModularPipeline.from_pretrained(
repo_id,
trust_remote_code=True,
)
pipe.load_components(dtype=torch.bfloat16)
pipe.to("cuda")
img = pipe(
prompt="...",
height=4096,
width=4096,
).images[0]
```
Both implementations address open `diffusers` requests (#14480, #14520).
Check out the collection! https://huggingface.co/collections/remyxai/training-free-high-resolution-generation-with-flux reacted to salma-remyx's post with 🚀 27 minutes ago
We just published two training-free 🧩 Modular Diffusers community pipelines that push off-the-shelf FLUX to 4096².
No fine-tuning, no extra weights, no upscaler.
The methods take different routes around positional extrapolation:
âś… **HRDiT:** resolution ladder + NTK RoPE + spatial-position alignment + structure guidance
✅ **DyPE:** single-pass, timestep-dynamic RoPE (κ=t²), plus an optional SEGA spectral mode that removes high-frequency speckle
Because both expose the same block interface, you can A/B the two methods on the same FLUX.1-Krea-dev weights by swapping the repo ID:
```python
import torch
from diffusers import ModularPipeline
repo_id = "remyxai/dype-flux-modular"
# or "remyxai/hrdit-flux-modular"
pipe = ModularPipeline.from_pretrained(
repo_id,
trust_remote_code=True,
)
pipe.load_components(dtype=torch.bfloat16)
pipe.to("cuda")
img = pipe(
prompt="...",
height=4096,
width=4096,
).images[0]
```
Both implementations address open `diffusers` requests (#14480, #14520).
Check out the collection! https://huggingface.co/collections/remyxai/training-free-high-resolution-generation-with-flux reacted to salma-remyx's post with 🔥 27 minutes ago
If you can’t explain why your AI-generated contribution belongs in the repo, don’t put it in a maintainer’s queue 🙅🏻‍♀️
Before asking for review, you should be able to answer:
1. What project need does it address?
2. Where does it fit, and does it duplicate existing work?
3. What evidence shows it works, and will you own it through review?
If you can’t answer those, you haven’t saved anyone time. You’ve passed the buck to the maintainer.
Outrider has made us better contributors by doing more of this work before upstream review by
* reading contribution rules, accepted PRs, and open issues
* finding needs and integration points
* drafting the code, tests, and context.
We still decide what deserves to go upstream, verify the claims, coordinate with maintainers and contributors, and stay involved through review.
On huggingface/peft, only 4 of 20 Outrider runs opened draft PRs. Two contributions have now merged:
âś… Riemannian-preconditioned LoRA: https://github.com/huggingface/peft/pull/3382
âś… Super-Tuning: https://github.com/huggingface/peft/pull/3518
We have more contributions in review and far more ideas were filtered out before they reached a maintainer.
Full case study: https://remyx.ai/case-study
Outrider: https://github.com/remyxai/outriderOrganizations
None yet