Hugging Face's logo

The-frizzy1
/
LTX2-GGUF-workflow

Image-to-Video
GGUF
comfyui
workflow
ltxv2
low-vram
text-to-video
beginner-friendly
Model card Files
xet
 Community
The-frizzy1 commited on
Commit
303b9e7
·
verified ·
1 Parent(s): c06b142

Update README with video links and full documentation

Browse files
Files changed (1) hide show
  1. README.md +67 -33
README.md CHANGED
@@ -1,51 +1,85 @@
1
- LTXV-2 GGUF ComfyUI Workflow
 
 
 
 
 
 
 
 
 
 
 
2
 
3
- A simple, color-coded GGUF workflow for running LTXV-2 in ComfyUI.
4
- Designed to be straightforward and lightweight.
5
 
 
 
 
 
6
 
7
- Tested Hardware
8
- Most videos: RTX 3060 (12GB VRAM) + 48GB RAM
9
- Works on RTX 3050 Laptop (4GB VRAM) + 16GB RAM (enable Triton)
10
- Common Issues
11
- Error: LTXVEmptyLatentAudio – AttributeError
12
 
13
- Update Kijai Node Pack to v1.2.8
14
 
15
- Checkerboard / patterned noise output
16
 
17
- Update all nodes + ComfyUI
18
- (Outdated GGUF loader or ComfyUI build)
19
 
20
- Required Node Packs
21
- ComfyUI-GGUF
22
- https://github.com/city96/ComfyUI-GGUF
23
 
24
- ComfyUI-KJNodes
25
- https://github.com/kijai/ComfyUI-KJNodes (install & update it!)
26
 
27
- REQUIRED Models
28
- Main Directory:
 
 
29
 
30
- https://huggingface.co/Kijai/LTXV2_comfy/tree/main/
31
 
32
- You need to download following models:
33
 
34
- Diffusion (dev Q4_k_m less vram Q8_0 more vram):
35
- https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/diffusion_models/ltx-2-19b-dev_Q4_K_M.gguf
36
 
37
- https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/diffusion_models/ltx-2-19b-dev_Q8_0.gguf
38
 
39
- Text Encoders (Gemma3 smaller files less vram, connector) Both are required:
40
- https://huggingface.co/Comfy-Org/ltx-2/tree/main/split_files/text_encoders
41
- https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/text_encoders/ltx-2-19b-embeddings_connector_dev_bf16.safetensors
42
 
43
- VAE (bf16 audio + video) Both are required: https://huggingface.co/Kijai/LTXV2_comfy/tree/main/VAE
 
 
 
44
 
45
- Latent Upscaler: https://huggingface.co/Lightricks/LTX-2/tree/main/ltx-2-spatial-upscaler-x2-1.0.safetensors
46
 
47
- LoRAs
48
- Distilled: https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/loras/ltx-2-19b-distilled-lora_resized_dynamic_fro09_avg_rank_175_fp8.safetensors
49
 
50
- (Optional)
51
- Camera: https://huggingface.co/Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left/tree/main
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - comfyui
5
+ - workflow
6
+ - ltxv2
7
+ - gguf
8
+ - low-vram
9
+ - text-to-video
10
+ - image-to-video
11
+ - beginner-friendly
12
+ ---
13
 
14
+ # LTX2 GGUF — Low VRAM Video Generation (I2V / T2V)
 
15
 
16
+ **By:** [The_frizzy1](https://civitai.com/user/The_frizzy1)
17
+ **Hardware target:** RTX 3050 (4 GB) / RTX 3060 (12 GB)
18
+ **CivitAI:** https://civitai.com/models/2339823/ltx2-gguf-low-vram-video-generation-i2v-t2v
19
+ **YouTube:** https://www.youtube.com/@the_frizzy1
20
 
21
+ 🎥 **Video Explainer:** https://www.youtube.com/watch?v=nnHUBMgdJac
 
 
 
 
22
 
23
+ ---
24
 
25
+ ## What This Is
26
 
27
+ Simple color-coded GGUF workflow for LTXV-2 in ComfyUI. Lightweight, I2V and T2V support.
 
28
 
29
+ ---
 
 
30
 
31
+ ## Tested Hardware
 
32
 
33
+ | Hardware | Notes |
34
+ |----------|-------|
35
+ | RTX 3060 12GB + 48GB RAM | Main test hardware |
36
+ | RTX 3050 4GB + 16GB RAM | Enable Triton |
37
 
38
+ ---
39
 
40
+ ## Common Issues
41
 
42
+ - `LTXVEmptyLatentAudio – AttributeError` → Update KJNodes to v1.2.8+
43
+ - Checkerboard noise → Update all nodes + ComfyUI
44
 
45
+ ---
46
 
47
+ ## Required Custom Nodes
 
 
48
 
49
+ | Node | Link |
50
+ |------|------|
51
+ | ComfyUI-GGUF | https://github.com/city96/ComfyUI-GGUF |
52
+ | KJNodes *(keep updated!)* | https://github.com/kijai/ComfyUI-KJNodes |
53
 
54
+ ---
55
 
56
+ ## Model Downloads
 
57
 
58
+ Main: https://huggingface.co/Kijai/LTXV2_comfy/tree/main/
59
+
60
+ **Diffusion (pick one):**
61
+ | File | VRAM |
62
+ |------|------|
63
+ | [Q4_K_M](https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/diffusion_models/ltx-2-19b-dev_Q4_K_M.gguf) | Less |
64
+ | [Q8_0](https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/diffusion_models/ltx-2-19b-dev_Q8_0.gguf) | More / better |
65
+
66
+ **Text Encoders (both required):**
67
+ - https://huggingface.co/Comfy-Org/ltx-2/tree/main/split_files/text_encoders
68
+ - https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/text_encoders/ltx-2-19b-embeddings_connector_dev_bf16.safetensors
69
+
70
+ **VAE (both files):** https://huggingface.co/Kijai/LTXV2_comfy/tree/main/VAE
71
+
72
+ **Upscaler:** https://huggingface.co/Lightricks/LTX-2/tree/main/ltx-2-spatial-upscaler-x2-1.0.safetensors
73
+
74
+ **LoRAs:**
75
+ - [Distilled](https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/loras/ltx-2-19b-distilled-lora_resized_dynamic_fro09_avg_rank_175_fp8.safetensors)
76
+ - [Camera Dolly Left *(optional)*](https://huggingface.co/Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left/tree/main)
77
+
78
+ ---
79
+
80
+ ## Changelog
81
+
82
+ | Version | Notes |
83
+ |---------|-------|
84
+ | v1.5 | Current release |
85
+ | v1.0 | Initial release |