Video-to-Video
Diffusers
English
Chinese
video-editing
streaming
quantization
int8
text-stream-stripping
Instructions to use kylinfires/Joy-face_change_optimized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kylinfires/Joy-face_change_optimized with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kylinfires/Joy-face_change_optimized", 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
Commit History
6 days ago
-
Sync main: ROCm SDPA fallback (RX 6900 XT)
Verified signaturec645730 -
Sync main: 720x408 8 GB sweet spot + ref basesize knob
Verified signatureb38e98d -
Sync main: low-VRAM live test results (624x360)
Verified signatureb9fc164
7 days ago
-
Sync main 10a0342: prefetch gate, desktop launcher, README
Verified signature9a0d910 -
Sync main 926df26: text pager (3.8 s first prompt) + 8 GB streaming mode
Verified signature4c04645 -
Sync main 91da25b: text K/V host cache (repeat sessions 1.4 s) + audit fixes
Verified signature9f083fb -
Sync main b2907cd: audited README (units + text-KV row) and MEM report fix
Verified signature2c4d1d0 -
Sync main 7ac17e9: reference-KV reuse, FP8 head option, measured follow-ups
Verified signaturea54a7fd -
Sync to 0da828a: int8 K/V cache option, reproducible sessions
Verified signature23f5a4d -
Sync to 5cc6520: per-step text K/V cache, text-stream offload, tight-VRAM mode (15.3 GiB), measured results in README
Verified signature32706ed -
JoyAI-Video-Edit fork: int4/int8 quantization tooling, portable fused-op fallback, dark UI
Verified signature65ad303