Create README.md

README.md

@@ -0,0 +1,27 @@
+---
+base_model:
+- rain1011/pyramid-flow-sd3
+pipeline_tag: text-to-video
+library_name: diffusers
+---
+
+Converted to bfloat16 from [rain1011/pyramid-flow-sd3](https://huggingface.co/rain1011/pyramid-flow-sd3). Use the text encoders and tokenizers from that repo (or from SD3), no point reuploading them over and over unchanged.
+
+Inference code is available here: [github.com/jy0205/Pyramid-Flow](https://github.com/jy0205/Pyramid-Flow/tree/main).
+
+Both 384p and 768p work on 24 GB VRAM. For 16 steps (5 second video), 384p takes a little over a minute on a 3090, and 768p takes about 7 minutes. For 31 steps (10 second video), 384p took about 10 minutes.
+
+In `diffusion_schedulers/scheduling_flow_matching.py`, in the function `init_sigmas_for_each_stage`, one small change needs to be made:
+
+Change this line:
+```
+self.timesteps_per_stage[i_s] = torch.from_numpy(timesteps[:-1])
+```
+To this:
+```
+self.timesteps_per_stage[i_s] = timesteps[:-1]
+```
+
+This will allow the model to be compatible with newer versions of pytorch and other libraries than is shown in the requirements.
+
+Working with torch2.4.1+cu124.