Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

One reference sheet. Full creative control. LTX-2.3 IC-LoRA Ingredients locks your character, prop, and location off a single reference sheet, then carries all three into your generated video.

ltx_io's profile picture

LTX.io

39,240 subscribers

14,295 Aufrufe • vor 2 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Using reference sheets with Omni has now become my favorite method for consistent storytelling with AI so I built a Freepik space that allows you to generate these reference sheets (characters & items) with ease, here you go This method allows you to add a character reference sheet, item reference sheet and a location and combine all elements into a single video with multiple camera angle changes using Kling AI 3.0's Omni feature. This feature works wonderfully for consistent storytelling. Enjoy!👍
1:58

Using reference sheets with Omni has now become my favorite method for consistent storytelling with AI so I built a Freepik space that allows you to generate these reference sheets (characters & items) with ease, here you go This method allows you to add a character reference sheet, item reference sheet and a location and combine all elements into a single video with multiple camera angle changes using Kling AI 3.0's Omni feature. This feature works wonderfully for consistent storytelling. Enjoy!👍

Travis Davids

20,757 Aufrufe • vor 6 Monaten

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai
1:15

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai

Kōda

166,497 Aufrufe • vor 5 Monaten

Tired of LTX 2.3 changing your character's face halfway through a video? ❌👤 Meet Best Face ID, the ultimate consistency LoRA for LTX 2.3! ✅ Single-photo face locking ✅ 4-Column Character Sheet support (Front/Side/Back) ✅ 2K Tiled Upscaling Workflows Pro Tip: Your prompt MUST start with ref_t2v: for it to lock properly. Full tutorial & 4 ComfyUI workflows: 👇 🔗 #BestFaceID #LTX23 #ComfyUI #AIVideo #CharacterConsistency #人工智能
1:19

Tired of LTX 2.3 changing your character's face halfway through a video? ❌👤 Meet Best Face ID, the ultimate consistency LoRA for LTX 2.3! ✅ Single-photo face locking ✅ 4-Column Character Sheet support (Front/Side/Back) ✅ 2K Tiled Upscaling Workflows Pro Tip: Your prompt MUST start with ref_t2v: for it to lock properly. Full tutorial & 4 ComfyUI workflows: 👇 🔗 #BestFaceID #LTX23 #ComfyUI #AIVideo #CharacterConsistency #人工智能

有趣的80后程序员

15,120 Aufrufe • vor 1 Monat

Create amazing action scenes with Seedance 2.0! First, create your character sheet with ChatGPT Images 2.0, then bring it to Seedance 2.0 as a reference image. Prompt your scene and what happens, referencing the character. More details + prompts below.
0:28

Create amazing action scenes with Seedance 2.0! First, create your character sheet with ChatGPT Images 2.0, then bring it to Seedance 2.0 as a reference image. Prompt your scene and what happens, referencing the character. More details + prompts below.

Jerrod Lew

15,877 Aufrufe • vor 4 Monaten

Instead of prompting with text only, create reference sheets first. Prompts in the comments 👇👇 For a yoga / wellness influencer video, I build: First 15 seconds - Motion sheet - the exact routine, poses, timing, transitions Character sheet - same face, body, outfit, expressions Location sheet -studio, lighting, props, mood, camera fee second 15 seconds - i put all 3 in one image. see the difference. 3 different sheets works better
0:30

Instead of prompting with text only, create reference sheets first. Prompts in the comments 👇👇 For a yoga / wellness influencer video, I build: First 15 seconds - Motion sheet - the exact routine, poses, timing, transitions Character sheet - same face, body, outfit, expressions Location sheet -studio, lighting, props, mood, camera fee second 15 seconds - i put all 3 in one image. see the difference. 3 different sheets works better

Dheepan Ratnam

31,313 Aufrufe • vor 4 Monaten

We just open-sourced 3DREAL ! A new render-to-real IC-LoRA for LTX-2.3 from fal: turn any 3D / CG / game render into high 3d render, photorealistic, film-quality video, keeping your exact composition and camera move using the first frame.
0:57

We just open-sourced 3DREAL ! A new render-to-real IC-LoRA for LTX-2.3 from fal: turn any 3D / CG / game render into high 3d render, photorealistic, film-quality video, keeping your exact composition and camera move using the first frame.

fal

216,603 Aufrufe • vor 3 Monaten

A Chinese creator found a way to sell $3,000-$5,000 brand videos with no team, no camera crew, and no agency. no film crew. no editor. no storyboard artist. just one ComfyUI canvas turning product photos into finished AI ads. > GPT-image2 builds the director board: shots, camera moves, scenes, sound design > Seedance 2.0 turns the board into motion > product reference locks the object > character reference locks the face, outfit, and style > 16:9. 4K. one visual plan. > final prompt: generate the video from this storyboard old workflow: brand → agency → director → editor → revisions → invoice new workflow: product image → storyboard → reference sheet → video the expensive part was never rendering.
2:03

A Chinese creator found a way to sell $3,000-$5,000 brand videos with no team, no camera crew, and no agency. no film crew. no editor. no storyboard artist. just one ComfyUI canvas turning product photos into finished AI ads. > GPT-image2 builds the director board: shots, camera moves, scenes, sound design > Seedance 2.0 turns the board into motion > product reference locks the object > character reference locks the face, outfit, and style > 16:9. 4K. one visual plan. > final prompt: generate the video from this storyboard old workflow: brand → agency → director → editor → revisions → invoice new workflow: product image → storyboard → reference sheet → video the expensive part was never rendering.

0xTria

16,251 Aufrufe • vor 3 Monaten

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.
0:25

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.

Jerrod Lew

30,665 Aufrufe • vor 1 Jahr

Today we're launching three new LoRAs for our open source video model, LTX Video! 🕺 Pose LoRA 🏞️ Depth LoRA ✏️ Canny LoRA Get unprecedented control over your AI videos and train new control types with just a few samples on consumer hardware. Details below 👇
0:33

Today we're launching three new LoRAs for our open source video model, LTX Video! 🕺 Pose LoRA 🏞️ Depth LoRA ✏️ Canny LoRA Get unprecedented control over your AI videos and train new control types with just a few samples on consumer hardware. Details below 👇

LTX.io

140,132 Aufrufe • vor 1 Jahr

Workflow: Made this cinematic football short with a surprisingly simple workflow: - Created the character sheet in ChatGPT - Generated 3 connected storyboards (10 frames each) - Converted each storyboard into a detailed Seedance 2.0 video prompt - Generated all scenes in Seedance - Edited everything together into one film Character → Storyboards → Video Prompts → Seedance → Final Film.
0:36

Workflow: Made this cinematic football short with a surprisingly simple workflow: - Created the character sheet in ChatGPT - Generated 3 connected storyboards (10 frames each) - Converted each storyboard into a detailed Seedance 2.0 video prompt - Generated all scenes in Seedance - Edited everything together into one film Character → Storyboards → Video Prompts → Seedance → Final Film.

Beginnersblog

39,727 Aufrufe • vor 3 Monaten

What a difference 2 weeks can make. We launched Veo 2, released LTX Video 13B, and brought them together with LTXV Turbo in a single platform. Three powerful models. One creative workflow. All in LTX Studio.
0:56

What a difference 2 weeks can make. We launched Veo 2, released LTX Video 13B, and brought them together with LTXV Turbo in a single platform. Three powerful models. One creative workflow. All in LTX Studio.

LTX.io

18,190 Aufrufe • vor 1 Jahr

ComfyUI for Advertising: Storyboards & Style Frames from a Shot List Shot list → storyboard → style frames. Two passes, one graph. Pass 1: type your shots into the shot list node. GPT Image returns all 9 panels as a single sketch sheet, plus each panel saved out on its own. Product image optional as reference. Pass 2: hand that sheet + a mood board to Nano Banana Pro. Every panel comes back as commercial photography, graded to your board. Works with hand-drawn boards too.
1:14

ComfyUI for Advertising: Storyboards & Style Frames from a Shot List Shot list → storyboard → style frames. Two passes, one graph. Pass 1: type your shots into the shot list node. GPT Image returns all 9 panels as a single sketch sheet, plus each panel saved out on its own. Product image optional as reference. Pass 2: hand that sheet + a mood board to Nano Banana Pro. Every panel comes back as commercial photography, graded to your board. Works with hand-drawn boards too.

ComfyUI

13,274 Aufrufe • vor 16 Tagen

Seedance 2.5 Storyboard Director, a free Claude skill. Your storyboard isn't doing anything. You draw it. You upload it. Seedance 2.5 renders something else and you blame the model. It isn't the model. A board with no panel to timestamp mapping is just another style reference. Nothing tells Seedance 2.5 those panels are the shot order. So I built the mapping in: → Timestamped storyboard sheet prompts. → Character sheet prompts with face lock. → Video prompts where every beat carries its panel code. → A locked @ reference order that stops character drift. → Exclusion lines that keep panel borders and gray backdrops out. → 10 intake questions, each with a default. Prompts, not images. Paste them into whatever image model you run. Free download in the reply.
0:30

Seedance 2.5 Storyboard Director, a free Claude skill. Your storyboard isn't doing anything. You draw it. You upload it. Seedance 2.5 renders something else and you blame the model. It isn't the model. A board with no panel to timestamp mapping is just another style reference. Nothing tells Seedance 2.5 those panels are the shot order. So I built the mapping in: → Timestamped storyboard sheet prompts. → Character sheet prompts with face lock. → Video prompts where every beat carries its panel code. → A locked @ reference order that stops character drift. → Exclusion lines that keep panel borders and gray backdrops out. → 10 intake questions, each with a default. Prompts, not images. Paste them into whatever image model you run. Free download in the reply.

BMX

80,263 Aufrufe • vor 1 Monat

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇
0:49

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇

ComfyUI

19,041 Aufrufe • vor 5 Monaten

WAN 3.0 & 3.0 Prime are now live on Fotor. Speed without the quality trade-off. Create with more flexibility, more references, and more control: • Flexible image-to-video controls • Strong reference handling • 2-30 second video generation • Support for up to 20 assets From a single image to a multi-reference creative, bring your ideas to life faster without compromising on quality. Try WAN 3.0 & 3.0 Prime on Fotor today.
0:30

WAN 3.0 & 3.0 Prime are now live on Fotor. Speed without the quality trade-off. Create with more flexibility, more references, and more control: • Flexible image-to-video controls • Strong reference handling • 2-30 second video generation • Support for up to 20 assets From a single image to a multi-reference creative, bring your ideas to life faster without compromising on quality. Try WAN 3.0 & 3.0 Prime on Fotor today.

Fotor

26,332 Aufrufe • vor 1 Monat

I've been playing more with this depth map motion transfer workflow, and if you're trying to recreate really specific body movements from a reference video, this works surprisingly well. Here's the workflow: 1. Grab your reference video, then create your character and environment references. 2. Run the video through Depth Anything on fal to generate a depth map: 3. Drop that depth map into Seedance Omni as your motion reference along with your character and environment references. You don't even need the original video. I also tested this against using the original video as the motion reference in Seedance, and there's definitely a noticeable difference. One thing I found, though, is that this works much better for body movement than facial performance since the depth map can't really capture subtle facial motion. I'm running more tests to see if there's a good way to control both body movement and facial performance. If you have any workflows I should try, do share in the comments!
0:52

I've been playing more with this depth map motion transfer workflow, and if you're trying to recreate really specific body movements from a reference video, this works surprisingly well. Here's the workflow: 1. Grab your reference video, then create your character and environment references. 2. Run the video through Depth Anything on fal to generate a depth map: 3. Drop that depth map into Seedance Omni as your motion reference along with your character and environment references. You don't even need the original video. I also tested this against using the original video as the motion reference in Seedance, and there's definitely a noticeable difference. One thing I found, though, is that this works much better for body movement than facial performance since the depth map can't really capture subtle facial motion. I'm running more tests to see if there's a good way to control both body movement and facial performance. If you have any workflows I should try, do share in the comments!

Curious Refuge

16,487 Aufrufe • vor 1 Monat

Yesterday, we announced Veo 3.1 to give you more creative control over your generations. And to give you *even* more control, here's a tip for those times when you want to use more than three ingredients: combine multiple images into a collage and upload as one ingredient. #FindYourFlow
0:23

Yesterday, we announced Veo 3.1 to give you more creative control over your generations. And to give you *even* more control, here's a tip for those times when you want to use more than three ingredients: combine multiple images into a collage and upload as one ingredient. #FindYourFlow

Google Flow

30,165 Aufrufe • vor 11 Monaten

Wan2.1-VACE 14B & 1.3B are now natively supported in ComfyUI! This model from Wan brings all-in-one editing capability to your video generation: 🔹Text-to-Video & Image-to-Video 🔹 Video-to-video (Pose & depth control) 🔹 Inpainting & Outpainting 🔹 Character + object reference
0:36

Wan2.1-VACE 14B & 1.3B are now natively supported in ComfyUI! This model from Wan brings all-in-one editing capability to your video generation: 🔹Text-to-Video & Image-to-Video 🔹 Video-to-video (Pose & depth control) 🔹 Inpainting & Outpainting 🔹 Character + object reference

ComfyUI

21,517 Aufrufe • vor 1 Jahr