city96 commited on
Commit
f5ccd5a
·
verified ·
1 Parent(s): 776385e

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -0
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Lightricks/LTX-Video
3
+ library_name: gguf
4
+ quantized_by: city96
5
+ tags:
6
+ - ltx-video
7
+ - text-to-video
8
+ - image-to-video
9
+ language:
10
+ - en
11
+ license: other
12
+ license_link: LICENSE.md
13
+ ---
14
+
15
+ This is a direct GGUF conversion of [Lightricks/LTX-Video](https://huggingface.co/Lightricks/LTX-Video).
16
+
17
+ The model files can be used in [ComfyUI](https://github.com/comfyanonymous/ComfyUI/) with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node. Place the required model(s) in the following folders:
18
+
19
+ | Type | Name | Location | Download |
20
+ | ------------ | ------------------------- | --------------------------------- | ------ |
21
+ | Main Model | LTX-Video-0.9.6-Distilled | `ComfyUI/models/diffusion_models` | GGUF (this repo) |
22
+ | Text Encoder | T5-V1.1-XXL-Encoder | `ComfyUI/models/text_encoders` | [Safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main) / [GGUF](https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf) |
23
+ | VAE | LTX-Video-0.9.6-VAE | `ComfyUI/models/vae` | [Safetensors](https://huggingface.co/city96/LTX-Video-0.9.6-dev-gguf/blob/main/LTX-Video-0.9.6-VAE-BF16.safetensors) |
24
+
25
+ [**Example workflow**](media/ltx-video-2b-v0.9.6-distilled_workflow.json) - based on the [official example workflow](https://comfyanonymous.github.io/ComfyUI_examples/ltxv/)
26
+
27
+ [**Example outputs**](media/ltxv-2b-0.9.6-distilled-04-25.mp4) - sample size of 1, not strictly representative
28
+
29
+ <video controls autoplay loop muted src="https://cdn-uploads.huggingface.co/production/uploads/64ab1219a347b95719b96c10/XyiETp3wrHTljjHHEEUIG.mp4"></video>
30
+
31
+ ### Notes
32
+
33
+ The VAE seems to be largely the same as LTXV 0.9.5 and the difference between the two seems negligible, but I've uploaded the 0.9.6 one to this repo to be safe
34
+
35
+ *As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*