Switch base model to SulphurAI/Sulphur-2-base (fp8mixed transformer + Sulphur distill LoRA)
Browse files- README.md +3 -3
- pipeline.py +5 -5
README.md
CHANGED
|
@@ -47,10 +47,10 @@ holds a coffee cup in their right hand, glances to the left.
|
|
| 47 |
|
| 48 |
| Component | Source |
|
| 49 |
|-----------|--------|
|
| 50 |
-
| Transformer (22B, FP8) | [
|
| 51 |
| Video VAE | [Kijai/LTX2.3_comfy](https://huggingface.co/Kijai/LTX2.3_comfy) |
|
| 52 |
-
| Text encoder
|
| 53 |
-
|
|
| 54 |
| BFS head-swap LoRA | [Alissonerdx/BFS-Best-Face-Swap-Video](https://huggingface.co/Alissonerdx/BFS-Best-Face-Swap-Video) |
|
| 55 |
|
| 56 |
## Logs
|
|
|
|
| 47 |
|
| 48 |
| Component | Source |
|
| 49 |
|-----------|--------|
|
| 50 |
+
| Transformer (22B, FP8 mixed) | [SulphurAI/Sulphur-2-base](https://huggingface.co/SulphurAI/Sulphur-2-base) |
|
| 51 |
| Video VAE | [Kijai/LTX2.3_comfy](https://huggingface.co/Kijai/LTX2.3_comfy) |
|
| 52 |
+
| Text encoder + scheduler | [Lightricks/LTX-Video](https://huggingface.co/Lightricks/LTX-Video) |
|
| 53 |
+
| Distill LoRA | [SulphurAI/Sulphur-2-base](https://huggingface.co/SulphurAI/Sulphur-2-base) |
|
| 54 |
| BFS head-swap LoRA | [Alissonerdx/BFS-Best-Face-Swap-Video](https://huggingface.co/Alissonerdx/BFS-Best-Face-Swap-Video) |
|
| 55 |
|
| 56 |
## Logs
|
pipeline.py
CHANGED
|
@@ -2,10 +2,10 @@
|
|
| 2 |
LTX-2.3 inference pipeline for BFS head-swap.
|
| 3 |
|
| 4 |
Model sources:
|
| 5 |
-
Transformer :
|
| 6 |
-
Video VAE : Kijai/LTX2.3_comfy
|
| 7 |
Pipeline cfg: Lightricks/LTX-Video (text encoder, scheduler, tokenizer via from_pretrained)
|
| 8 |
-
LoRA
|
| 9 |
LoRA BFS : Alissonerdx/BFS-Best-Face-Swap-Video — ltx-2.3/head_swap_v3_rank_adaptive_fro_098.safetensors
|
| 10 |
"""
|
| 11 |
|
|
@@ -29,9 +29,9 @@ from PIL import Image
|
|
| 29 |
_HF_CACHE = os.environ.get("HF_HOME", os.path.expanduser("~/.cache/huggingface"))
|
| 30 |
|
| 31 |
MODELS = {
|
| 32 |
-
"transformer": ("
|
| 33 |
"video_vae": ("Kijai/LTX2.3_comfy", "vae/LTX23_video_vae_bf16.safetensors"),
|
| 34 |
-
"lora_motion": ("
|
| 35 |
"lora_bfs": ("Alissonerdx/BFS-Best-Face-Swap-Video", "ltx-2.3/head_swap_v3_rank_adaptive_fro_098.safetensors"),
|
| 36 |
}
|
| 37 |
|
|
|
|
| 2 |
LTX-2.3 inference pipeline for BFS head-swap.
|
| 3 |
|
| 4 |
Model sources:
|
| 5 |
+
Transformer : SulphurAI/Sulphur-2-base — sulphur_dev_fp8mixed.safetensors
|
| 6 |
+
Video VAE : Kijai/LTX2.3_comfy — vae/LTX23_video_vae_bf16.safetensors
|
| 7 |
Pipeline cfg: Lightricks/LTX-Video (text encoder, scheduler, tokenizer via from_pretrained)
|
| 8 |
+
LoRA distill: SulphurAI/Sulphur-2-base — distill_loras/ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors
|
| 9 |
LoRA BFS : Alissonerdx/BFS-Best-Face-Swap-Video — ltx-2.3/head_swap_v3_rank_adaptive_fro_098.safetensors
|
| 10 |
"""
|
| 11 |
|
|
|
|
| 29 |
_HF_CACHE = os.environ.get("HF_HOME", os.path.expanduser("~/.cache/huggingface"))
|
| 30 |
|
| 31 |
MODELS = {
|
| 32 |
+
"transformer": ("SulphurAI/Sulphur-2-base", "sulphur_dev_fp8mixed.safetensors"),
|
| 33 |
"video_vae": ("Kijai/LTX2.3_comfy", "vae/LTX23_video_vae_bf16.safetensors"),
|
| 34 |
+
"lora_motion": ("SulphurAI/Sulphur-2-base", "distill_loras/ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors"),
|
| 35 |
"lora_bfs": ("Alissonerdx/BFS-Best-Face-Swap-Video", "ltx-2.3/head_swap_v3_rank_adaptive_fro_098.safetensors"),
|
| 36 |
}
|
| 37 |
|