by SulphurAI
Sulphur 2 (base) is a 9B uncensored video generation model built on the LTX-2.3 architecture, supporting native text-to-video and image-to-video. Ships with a built-in prompt enhancer and quantized GGUF builds (~9.5GB Q8_0) for consumer hardware.
Your hardware
Detecting...
Measured quality metrics for Sulphur 2 outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
VRAM estimates at FP16 and FP8 precision. FP8 uses ~40% less memory with minimal quality loss. Grade shows how well each GPU handles the generation workload.
| Scenario | VRAM | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 · 25 frames | 34.5 GB | F | F | F | F |
| 768×512 · 25 frames | 36.6 GB | F | F | F | F |
| 768×512 · 100 frames | 42.9 GB | F | F | F | F |
| 1280×720 · 25 frames | 45.1 GB | F | F | F | F |
| Scenario | VRAM | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 · 25 frames | 20.2 GB | A | F | F | D |
| 768×512 · 25 frames | 22.3 GB | B | F | F | D |
| 768×512 · 100 frames | 28.6 GB | D | F | F | F |
| 1280×720 · 25 frames | 30.7 GB | D | F | F | F |
GGUF Q4 available
Quantized GGUF format for lower VRAM and smaller downloads
from diffusers import LTXConditionPipeline
import torch
pipe = LTXConditionPipeline.from_pretrained(
"SulphurAI/Sulphur-2-base",
torch_dtype=torch.bfloat16
)
pipe.to("cuda")
frames = pipe(
prompt="your prompt here",
num_inference_steps=8,
guidance_scale=1.0,
num_frames=121,
).frames[0]
# Save frames or export as videoGet started
Setup instructions for running Sulphur 2 locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/ (or ComfyUI/models/unet/ for GGUF)3. Launch ComfyUI
python main.pyVRAM allocation for 25 frames at 768×512 on RTX 4090 24GB
25 frames at 768×512, 30 steps, FP16.
Download Sulphur 2 in different precisions. Lower precision = less VRAM but slight quality loss.
New model with an emerging LoRA ecosystem.
Frequently asked questions
Sulphur 2 (9B parameters) requires approximately 36.6 GB of VRAM at FP16 precision for generating 25 frames at 768×512. Video generation typically requires more VRAM than image generation due to temporal attention layers.
Sulphur 2 exceeds the RTX 4090's 24 GB VRAM at FP16 for video generation. Consider reducing resolution, frame count, or using a GPU with more VRAM.
On a reference GPU (RTX 4090 24GB), Sulphur 2 generates a 25-frame video at 768×512 in approximately ~2m 38s at FP16 with 30 inference steps. Faster GPUs with higher memory bandwidth will reduce generation time.
Sulphur 2 supports up to 1280×720 resolution and 241 frames per generation at 30 FPS. Higher resolutions and frame counts require proportionally more VRAM.
See also