comi-logic/Wan2GP
7
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Vace Outpainting, new Depth extractor

Browse Source
This commit is contained in:
DeepBeepMeep
2025-06-19 15:59:47 +02:00
parent 188225cdd7
commit 4d202db319
27 changed files with 2023 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
finetunes/t2v_fusionix.json
View File

@@ -1,7 +1,7 @@
{
"model":
{
"name": "Wan text2video FusioniX 14B",
"name": "Wan2.1 text2video FusioniX 14B",
"architecture" : "t2v",
"description": "A powerful merged text-to-video model based on the original WAN 2.1 T2V model, enhanced using multiple open-source components and LoRAs to boost motion realism, temporal consistency, and expressive detail.",
"URLs": [

38
finetunes/t2v_sf.json Normal file
View File

@@ -0,0 +1,38 @@
{
"model": {
"name": "Wan2.1 text2video Self-Forcing 14B",
"architecture": "t2v",
"description": "This model is an advanced text-to-video generation model. This approach allows the model to generate videos with significantly fewer inference steps (4 or 8 steps) and without classifier-free guidance, substantially reducing video generation time while maintaining high quality outputs.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_quanto_bf16_int8.safetensors",
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_quanto_fp16_int8.safetensors"
],
"author": "https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill",
"auto_quantize": true
},
"negative_prompt": "",
"prompt": "",
"resolution": "832x480",
"video_length": 81,
"seed": -1,
"num_inference_steps": 4,
"guidance_scale": 1,
"flow_shift": 3,
"embedded_guidance_scale": 6,
"repeat_generation": 1,
"multi_images_gen_type": 0,
"tea_cache_setting": 0,
"tea_cache_start_step_perc": 0,
"loras_multipliers": "",
"temporal_upsampling": "",
"spatial_upsampling": "",
"RIFLEx_setting": 0,
"slg_switch": 0,
"slg_start_perc": 10,
"slg_end_perc": 90,
"cfg_star_switch": 0,
"cfg_zero_step": -1,
"prompt_enhancer": "",
"activated_loras": []
}

41
finetunes/vace_14B_sf.json Normal file
View File

@@ -0,0 +1,41 @@
{
"model": {
"name": "Vace Self-Forcing 14B",
"architecture": "vace_14B",
"modules": [
"vace_14B"
],
"description": "This model is a combination of Vace and an advanced text-to-video generation model. This approach allows the model to generate videos with significantly fewer inference steps (4 or 8 steps) and without classifier-free guidance, substantially reducing video generation time while maintaining high quality outputs.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_quanto_bf16_int8.safetensors",
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_quanto_fp16_int8.safetensors"
],
"author": "https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill",
"auto_quantize": true
},
"negative_prompt": "",
"prompt": "",
"resolution": "832x480",
"video_length": 81,
"seed": -1,
"num_inference_steps": 4,
"guidance_scale": 1,
"flow_shift": 3,
"embedded_guidance_scale": 6,
"repeat_generation": 1,
"multi_images_gen_type": 0,
"tea_cache_setting": 0,
"tea_cache_start_step_perc": 0,
"loras_multipliers": "",
"temporal_upsampling": "",
"spatial_upsampling": "",
"RIFLEx_setting": 0,
"slg_switch": 0,
"slg_start_perc": 10,
"slg_end_perc": 90,
"cfg_star_switch": 0,
"cfg_zero_step": -1,
"prompt_enhancer": "",
"activated_loras": []
}