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

LTXV and Flux updates

Browse Source
This commit is contained in:
deepbeepmeep
2025-07-21 09:37:52 +02:00
parent a356c6af4b
commit a1c228054c
36 changed files with 1285 additions and 2288 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
defaults/flux_dev.json Normal file
View File

@@ -0,0 +1,16 @@
{
"model": {
"name": "Flux 1 Dev 12B",
"architecture": "flux",
"description": "FLUX.1 Dev is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Flux/resolve/main/flux1-dev_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/Flux/resolve/main/flux1-dev_quanto_bf16_int8.safetensors"
],
"image_outputs": true,
"flux-model": "flux-dev"
},
"prompt": "draw a hat",
"resolution": "1280x720",
"video_length": 1
}

11
defaults/flux_dev_kontext.json
View File

@@ -1,12 +1,15 @@
{
"model": {
"name": "Flux Dev Kontext 12B",
"architecture": "flux_dev_kontext",
"description": "FLUX.1 Kontext is a 12 billion parameter rectified flow transformer capable of editing images based on instructions stored in the Prompt. Please be aware that Flux Kontext is picky on the resolution of the input image the output dimensions may not match the dimensions of the input image.",
"name": "Flux 1 Dev Kontext 12B",
"architecture": "flux",
"description": "FLUX.1 Kontext is a 12 billion parameter rectified flow transformer capable of editing images based on instructions stored in the Prompt. Please be aware that Flux Kontext is picky on the resolution of the input image and the output dimensions may not match the dimensions of the input image.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Flux/resolve/main/flux1_kontext_dev_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/Flux/resolve/main/flux1_kontext_dev_quanto_bf16_int8.safetensors"
]
],
"image_outputs": true,
"reference_image": true,
"flux-model": "flux-dev-kontext"
},
"prompt": "add a hat",
"resolution": "1280x720",

17
defaults/flux_schnell.json Normal file
View File

@@ -0,0 +1,17 @@
{
"model": {
"name": "Flux 1 Schnell 12B",
"architecture": "flux",
"description": "FLUX.1 Schnell is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. As a distilled model it requires fewer denoising steps.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Flux/resolve/main/flux1-schnell_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/Flux/resolve/main//flux1-schnell_quanto_bf16_int8.safetensors"
],
"image_outputs": true,
"flux-model": "flux-schnell"
},
"prompt": "draw a hat",
"resolution": "1280x720",
"num_inference_steps": 10,
"video_length": 1
}

17
defaults/ltxv_13B.json
View File

@@ -1,14 +1,19 @@
{
{
"model":
{
"name": "LTX Video 0.9.7 13B",
"name": "LTX Video 0.9.8 13B",
"architecture" : "ltxv_13B",
"description": "LTX Video is a fast model that can be used to generate long videos (up to 260 frames).It is recommended to keep the number of steps to 30 or you will need to update the file 'ltxv_video/configs/ltxv-13b-0.9.7-dev.yaml'.The LTX Video model expects very long prompts, so don't hesitate to use the Prompt Enhancer.",
"description": "LTX Video is a fast model that can be used to generate very very long videos (up to 1800 frames !).It is recommended to keep the number of steps to 30 or you will need to update the file 'ltxv_video/configs/ltxv-13b-0.9.8-dev.yaml'.The LTX Video model expects very long prompts, so don't hesitate to use the Prompt Enhancer.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv_0.9.7_13B_dev_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv_0.9.7_13B_dev_quanto_bf16_int8.safetensors"
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv_0.9.8_13B_dev_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv_0.9.8_13B_dev_quanto_bf16_int8.safetensors"
],
"LTXV_config": "ltx_video/configs/ltxv-13b-0.9.7-dev.yaml"
"preload_URLs" : [
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv-097-ic-lora-pose-control-diffusers.safetensors",
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv-097-ic-lora-depth-control-diffusers.safetensors",
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv-097-ic-lora-canny-control-diffusers.safetensors"
],
"LTXV_config": "ltx_video/configs/ltxv-13b-0.9.8-dev.yaml"
},
"num_inference_steps": 30
}

15
defaults/ltxv_distilled.json
View File

@@ -1,14 +1,15 @@
{
"model":
{
"name": "LTX Video 0.9.7 Distilled 13B",
"name": "LTX Video 0.9.8 Distilled 13B",
"architecture" : "ltxv_13B",
"description": "LTX Video is a fast model that can be used to generate long videos (up to 260 frames).This distilled version is a very fast version and retains a high level of quality. The LTX Video model expects very long prompts, so don't hesitate to use the Prompt Enhancer.",
"URLs": "ltxv_13B",
"loras": ["https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv_0.9.7_13B_distilled_lora128_bf16.safetensors"],
"loras_multipliers": [ 1 ],
"lock_inference_steps": true,
"LTXV_config": "ltx_video/configs/ltxv-13b-0.9.7-distilled.yaml"
"description": "LTX Video is a fast model that can be used to generate very long videos (up to 1800 frames !).This distilled version is a very fast version and retains a high level of quality. The LTX Video model expects very long prompts, so don't hesitate to use the Prompt Enhancer.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv_0.9.8_13B_distilled_dev_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/LTX_Video/resolve/main/ltxv_0.9.8_13B_distilled_quanto_bf16_int8.safetensors"
],
"preload_URLs" : "ltxv_13B",
"LTXV_config": "ltx_video/configs/ltxv-13b-0.9.8-distilled.yaml"
},
"num_inference_steps": 6
}

2
defaults/t2v_1.3B.json
View File

@@ -5,7 +5,7 @@
"architecture" : "t2v_1.3B",
"description": "The light version of the original Wan Text 2 Video model. Most other models have been built on top of it",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_text2video_1.3B_bf16.safetensors"
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_text2video_1.3B_mbf16.safetensors"
]
}
}

5
defaults/vace_1.3B.json
View File

@@ -3,9 +3,8 @@
{
"name": "Vace ControlNet 1.3B",
"architecture" : "vace_1.3B",
"modules": ["vace_1.3B"],
"description": "The Vace ControlNet model is a powerful model that allows you to control the content of the generated video based of additional custom data : pose or depth video, images or objects you want to see in the video.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_Vace_1.3B_mbf16.safetensors"
]
"URLs": "t2v_1.3B"
}
}