TheMindExpansionNetwork commited on
Commit
3718ad0
·
verified ·
1 Parent(s): bb902db

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. README.md +62 -0
  2. lora_weights_step_02500.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - ltx-2
4
+ - ltx-video
5
+ - text-to-video
6
+ - audio-video
7
+ pinned: true
8
+ language:
9
+ - en
10
+ license: other
11
+ pipeline_tag: text-to-video
12
+ library_name: diffusers
13
+ ---
14
+
15
+ # questro_LTX
16
+
17
+ This is a fine-tuned version of [`ltx-2-19b-dev.safetensors`](/workspace/models/ltx2/ltx-2-19b-dev.safetensors) trained on custom data.
18
+
19
+ ## Model Details
20
+
21
+ - **Base Model:** [`ltx-2-19b-dev.safetensors`](/workspace/models/ltx2/ltx-2-19b-dev.safetensors)
22
+ - **Training Type:** LoRA fine-tuning
23
+ - **Training Steps:** 2500
24
+ - **Learning Rate:** 0.0001
25
+ - **Batch Size:** 1
26
+
27
+ ## Sample Outputs
28
+
29
+ | | | | |
30
+ |:---:|:---:|:---:|:---:|
31
+ | ![example1](./samples/sample_0.gif)<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>Questro is walking in a dystopian universe</details> |
32
+
33
+ ## Usage
34
+
35
+ This model is designed to be used with the LTX-2 (Lightricks Audio-Video) pipeline.
36
+
37
+ ### 🔌 Using Trained LoRAs in ComfyUI
38
+
39
+ In order to use the trained LoRA in ComfyUI, follow these steps:
40
+
41
+ 1. Copy your trained LoRA checkpoint (`.safetensors` file) to the `models/loras` folder in your ComfyUI installation.
42
+ 2. In your ComfyUI workflow:
43
+ - Add the "Load LoRA" node to choose your LoRA file
44
+ - Connect it to the "Load Checkpoint" node to apply the LoRA to the base model
45
+
46
+ You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the
47
+ official [LTX-2 repository](https://github.com/Lightricks/LTX-2).
48
+
49
+ ### Example Prompts
50
+
51
+ Example prompts used during validation:
52
+
53
+ - `Questro is walking in a dystopian universe`
54
+
55
+
56
+
57
+ This model inherits the license of the base model ([`ltx-2-19b-dev.safetensors`](/workspace/models/ltx2/ltx-2-19b-dev.safetensors)).
58
+
59
+ ## Acknowledgments
60
+
61
+ - Base model: [Lightricks](https://huggingface.co/Lightricks/LTX-2)
62
+ - Trainer: [LTX-2](https://github.com/Lightricks/LTX-2)
lora_weights_step_02500.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89dde92f1ea617d757b2fecae0a52f3c780af3ffe839648ff95147303ea8f0aa
3
+ size 402757824