Instructions to use InstantX/flux-dev-de-distill-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use InstantX/flux-dev-de-distill-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("InstantX/flux-dev-de-distill-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update pipeline_flux_de_distill.py
Browse files
pipeline_flux_de_distill.py
CHANGED
|
@@ -739,7 +739,7 @@ class FluxPipeline(DiffusionPipeline, FluxLoraLoaderMixin, FromSingleFileMixin):
|
|
| 739 |
timestep = t.expand(latent_model_input.shape[0])
|
| 740 |
|
| 741 |
noise_pred = self.transformer(
|
| 742 |
-
hidden_states=
|
| 743 |
timestep=timestep / 1000,
|
| 744 |
pooled_projections=pooled_prompt_embeds,
|
| 745 |
encoder_hidden_states=prompt_embeds,
|
|
|
|
| 739 |
timestep = t.expand(latent_model_input.shape[0])
|
| 740 |
|
| 741 |
noise_pred = self.transformer(
|
| 742 |
+
hidden_states=latent_model_input,
|
| 743 |
timestep=timestep / 1000,
|
| 744 |
pooled_projections=pooled_prompt_embeds,
|
| 745 |
encoder_hidden_states=prompt_embeds,
|