Skip to content

feat(flux2klein): Faster Loading + Compliation #456

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
amepas wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(flux2klein): Faster Loading + Compliation #456

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion src/maxdiffusion/configs/base_flux2klein.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -203,7 +203,7 @@ num_train_epochs: 1
seed: 0
output_dir: 'output/'
output_name: "flux2klein_generated_image.png"
per_device_batch_size: 1
per_device_batch_size: 1.0

warmup_steps_fraction: 0.1
learning_rate_schedule_steps: -1 # By default the length of the schedule is set to the number of steps.
Expand Down Expand Up @@ -231,6 +231,7 @@ do_classifier_free_guidance: True
guidance_scale: 4.0
guidance_rescale: 0.0
num_inference_steps: 4
num_reps: 1
save_final_checkpoint: False

# SDXL Lightning parameters
Expand Down
3 changes: 2 additions & 1 deletion src/maxdiffusion/configs/base_flux2klein_9B.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -203,7 +203,7 @@ num_train_epochs: 1
seed: 0
output_dir: 'output/'
output_name: "flux2klein_generated_image.png"
per_device_batch_size: 1
per_device_batch_size: 1.0

warmup_steps_fraction: 0.1
learning_rate_schedule_steps: -1 # By default the length of the schedule is set to the number of steps.
Expand Down Expand Up @@ -231,6 +231,7 @@ do_classifier_free_guidance: True
guidance_scale: 4.0
guidance_rescale: 0.0
num_inference_steps: 4
num_reps: 1
save_final_checkpoint: False

# SDXL Lightning parameters
Expand Down
355 changes: 220 additions & 135 deletions src/maxdiffusion/generate_flux2klein.py
View file
Open in desktop

Large diffs are not rendered by default.

8 changes: 7 additions & 1 deletion src/maxdiffusion/max_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -383,7 +383,13 @@ def device_put_replicated(x, sharding):
Although the name indicates replication, this function can be used
to also shard an array based on sharding.
"""
return jax.make_array_from_callback(x.shape, sharding, lambda index: x[index])
arr = getattr(x, "value", x)
shd = getattr(sharding, "value", sharding)
res = jax.make_array_from_callback(arr.shape, shd, lambda index: arr[index])
if hasattr(x, "set_value"):
x.set_value(res)
return x
return res


def fill_unspecified_mesh_axes(parallelism_vals, target_product, parallelism_type):
Expand Down
Loading
Loading