Thibaud Zamora ∞ @thibaudz Twitter profile

Pinned Tweet

Thibaud Zamora ∞

8 months

Join my mailing list for the latest A.I. insights 🤖. No spam, just fascinating updates, and breakthroughs in artificial intelligence. Subscribe here and let's explore the future together: 💡

3

1

35

Last Seen Profiles

@BigAss1714975

@Mmgl19037403

@EndemolShineIND

@TWMcQ55

@AliHasa01002719

@SBSVoices

@__15___15__

@capizzi_an26164

@vanizelemos

@mimona0611

@TasyaLina14

@maia_regle

@Darko522076411

@SWSchicago

@fulloflechuga

@NinoRod35868677

@Empire_Strykers

@ThKasparrr

@STELCOMALDIVES

@jacobs_divan

@big_boobs_gifs

@Dont72476981741

@Mits_Room2

@thomasvanschaik

@keira_math84009

@mariaga15962342

@floyzinho

@eileenjforrest

@shinseka_infor

@idobadtakes

@StephanieDassas

@KanjiEsports

@dlcofficial

@Slaigod

@KinFilmFestival

@Mkinthemost

Thibaud Zamora ∞

@thibaudz

9 months

Incredible! The integration of the amber in a real video, with the light of the phone!

37

361

3K

Thibaud Zamora ∞

@thibaudz

7 months

Testing Vid2Vid with HotShotXL & Comfy. The next step is to greenscreen it and add a static background.

30

184

1K

Thibaud Zamora ∞

@thibaudz

6 months

Bye Bye LoRA Bye Bye IPAdapter Hello dreamtuner-diffusion Full consistency with only one input image! Incredible (but code is not released yet...)

31

158

1K

Thibaud Zamora ∞

@thibaudz

8 months

2D to 3D is coming! 2024 will be the year of 3D with AI. DreamCraft3D looks promising (code "soon"). Even if the render is not perfect yet, it's not an issue. It'll be better once fine-tuned and with new research on it! And more important I already know how I'll use it🧶

54

141

1K

Thibaud Zamora ∞

@thibaudz

8 months

Stability just announced the private beta for their 3D model (Stable 3D). Many information about it in the thread! 1) A video demo. For a first beta, it looks very impressive!

20

131

600

Thibaud Zamora ∞

@thibaudz

2 years

Superheroes! #stablediffusion #DeforumDiffusion

20

96

579

Thibaud Zamora ∞

@thibaudz

7 months

Shocking Crossover: Harry Potter x Star Wars by Pixar, Holiday Special (Not Yet on Disney+) ✍️ Scenario: Human + GPT 🖼️ Image: SDXL / ComfyUI 🎥 Video: @pika_labs 🎙️ Voice: @coqui_ai Consistent Characters: IPAdapter & Prompt Interested in discovering the detailed process

40

135

547

Thibaud Zamora ∞

@thibaudz

2 years

#Stablediffusion - technical test.

13

44

516

Thibaud Zamora ∞

@thibaudz

6 months

Huge progress on the clothes tool!

23

62

518

Thibaud Zamora ∞

@thibaudz

1 year

Breaking News - Oops I did it again I just released 4 new ControlNet models for Stablediffusion 2.X - Normal Map (BAE) 🎨 - Segmentation (ADE20K) 🧩 - LineArt 🖼️ - Openpose with hands 🖐️ and face 🙂 Example and useful infos in thread ⏬ Important to read it until the end!

16

79

515

Thibaud Zamora ∞

@thibaudz

1 year

BREAKING NEWS Perpetual ♾ Diffusion ☀🌑 models are available. Have fun with them. Based on the awesome SD2.1-768 by @StabilityAI ~250 hours to create the dataset ~50 000 images ~300 hours of training 42 epochs for the final versions 1/3

22

75

471

Thibaud Zamora ∞

@thibaudz

7 months

For a dozen days, I've been working on a simple but efficient workflow for upscale. I share many results and many ask to share. So I'm happy to announce today: my tutorial and workflow are available. Links in comments.

26

57

466

Thibaud Zamora ∞

@thibaudz

11 months

ControlNet "OpenPose" XL is released:

7

77

421

Thibaud Zamora ∞

@thibaudz

4 months

i don't use caps anymore but... WHAT THE F*** zero-shot vid2vid! papers ✅ code ✅ it use sd1.5 and ebsynth under the hood + their algorithm of intra/inter-frame and it's compatible with controlnet and lora! more example below

16

69

399

Thibaud Zamora ∞

@thibaudz

7 months

Mix Them All (My favorite the last ones with the jelly)

16

47

373

Thibaud Zamora ∞

@thibaudz

8 months

Good news of the day: IPadapter Plus face is released for SDXL! I need to add that to my workflow!

18

60

369

Thibaud Zamora ∞

@thibaudz

7 months

It's a major breakthrough! Still very early but I can "image-prompt" clothes now. Need a bigger dataset and much longer training. For now, I have the global vibes of the clothes, the next step is to match it closer!

28

55

344

Thibaud Zamora ∞

@thibaudz

2 years

Time is running out. #stablediffusion #DeforumDiffusion

11

57

308

Thibaud Zamora ∞

@thibaudz

9 months

Comparison of 4 lipsync methods on 3 different videos (Zoom matters!) Top left: wav2lip (mouth only) Top right: wav2lip (full) Bottom left: Video retalking Bottom right: SadTalker Video

22

37

299

Thibaud Zamora ∞

@thibaudz

2 years

Pirate wreck - 1 #AiArt #ArtistOnTwitter

19

36

259

Thibaud Zamora ∞

@thibaudz

3 months

32

46

277

Thibaud Zamora ∞

@thibaudz

7 months

Let me introduce you to the (re)dress workflow! More examples below (This one will NOT be shared for obvious reasons)

26

30

271

Thibaud Zamora ∞

@thibaudz

5 months

amazon broke the game of clothing tools... and it'll be not only for clothes the best part? they ll release the code!

14

42

268

Thibaud Zamora ∞

@thibaudz

2 years

The second time ever I use an init image on #discodiffusion Nice result :-)

29

39

256

Thibaud Zamora ∞

@thibaudz

7 months

Google just released a wonderful paper AND code! Consistent style generation withOUT fine-tuning. It could be a challenger to IPAdapter. Can't wait to try it in ComfyUI! More info in thread!

4

29

262

Thibaud Zamora ∞

@thibaudz

1 year

ControlNet (canny) for 2.1 is working and released! link in comment cc @StabilityAI @EMostaque

16

43

253

Thibaud Zamora ∞

@thibaudz

8 months

Zero-shot styling! 🤯🤯🤯 Just stumbled upon a tech wizardry in a research paper! Imagine turning the Eiffel Tower 🗼into a giant cactus 🌵 without training! Can't wait to play with it. (code not released yet) It will be so useful to ensure consistency for A.I. Movies!

8

44

245

Thibaud Zamora ∞

@thibaudz

3 months

the first episode of the first (AI) sitcom on 𝕏 featuring @elonmusk (more details below)

32

40

247

Thibaud Zamora ∞

@thibaudz

6 months

Thanks @replicate and @chigozienri to adapt my AutoCaption tool and offer a free webservice to use it! That's why opensourcing tool is important! (link in first comment)

14

30

222

Thibaud Zamora ∞

@thibaudz

7 months

For TikTok Dance, Right?

20

24

228

Thibaud Zamora ∞

@thibaudz

4 months

i have access to #sd3 so let's go for a community generation thread * comment with your prompt * i ll generate image (maybe not all of them and not instant, i ll do my best) * share the first message to spread the word you can use short or very long prompts, and you can use

135

43

218

Thibaud Zamora ∞

@thibaudz

4 months

a new tool for talking character: EMO. results seem very good even on non-realistic image. code is not available yet. i hope someone smart will modify the code to use video as input too!

22

29

218

Thibaud Zamora ∞

@thibaudz

20 days

you.are.not.ready.for.that (poke @LumaLabsAI )

19

25

215

Thibaud Zamora ∞

@thibaudz

8 months

Watch my 2min. tutorial in which I explain (and share!) my workflow using IP Adapter Plus with SDXL in Comfy UI: (link to the tutorial in the first comment)

3

29

205

Thibaud Zamora ∞

@thibaudz

7 months

A new challenger for 2D-to-3D! Transform a single photo into a 3D masterpiece in under a minute with One-2-3-45++!

10

33

205

Thibaud Zamora ∞

@thibaudz

1 year

Progress of ControlNet - Depth V2 - 100% of the dataset downloaded - 75% of the preprocessing version done - Script for training done - The training will start in 9 hours 🤞 Next: write the annotator for the Automatic1111 ControlNet extension and test it! We can't know yet if

11

15

203

Thibaud Zamora ∞

@thibaudz

9 months

New paper "Deep Geometrized Cartoon Line Inbetweening". Demos are pretty good. Code and weight are available. The real question now is how can we leverage that to do a nice things for StableDiffusion (controlnet?/Animatediff?) poke

4

31

200

Thibaud Zamora ∞

@thibaudz

5 months

new model by stability: stable cascade (cascade because it s 3 different models used one after one) results are announced better and faster than sdxl can’t wait to try it in comfyui (once ipadapter will be available)

14

34

199

Thibaud Zamora ∞

@thibaudz

1 year

Test of the day.

17

22

191

Thibaud Zamora ∞

@thibaudz

7 months

SDXL Turbo is fast but not good for 1024x1024 SDXL DPO achieves better quality but is slow. SDXL DPO TURBO is amazing! Having a link to download this merge is 🥰(just look in the first comment) <- DPO TURBO ........ TURBO ->

10

33

195

Thibaud Zamora ∞

@thibaudz

7 months

Some progress to "img prompt" the new clothes. It's not the same but we got the vibes. More examples below.

10

24

194

Thibaud Zamora ∞

@thibaudz

2 years

Still working on my model. raw output + upscale #stablediffusion

10

11

178

Thibaud Zamora ∞

@thibaudz

7 months

Ever heard ofscreenshot-to-code? It's a game-changer for web development! This tool transforms any screenshot into HTML/Tailwind/JS code using GPT-4 Vision and DALL-E 3. And with CogVLM and Stable Diffusion, we can do a full open-source version of it now!

9

42

182

Thibaud Zamora ∞

@thibaudz

3 months

Dear @chrlaf , CTO and interim co-CEO of Stability, On behalf of the StableDiffusion user community, we are writing to express our concerns over the departure of Emad, who was a driving force behind Stability's open-source model training initiatives. Emad's commitment to

5

26

183

Thibaud Zamora ∞

@thibaudz

2 years

Will the pirates found Treasure or ... death? RT appreciated! #discodiffusion #digitalart

8

44

175

Thibaud Zamora ∞

@thibaudz

2 years

#stablediffusion

8

21

175

Thibaud Zamora ∞

@thibaudz

6 months

Amazing Dress Workflow Update! 🌟 Good News: I'm sharing it soon. ❌Bad News: No tutorial about it this week. 🚨 Must-Read: Exclusive beta workflow drops Friday for my mailing list subscribers! Don't miss out, sign up now! Link below 👇

11

25

177

Thibaud Zamora ∞

@thibaudz

2 years

probably nothing #stablediffusion

12

23

168

Thibaud Zamora ∞

@thibaudz

1 year

#stablediffusion #deforum

9

15

169

Thibaud Zamora ∞

@thibaudz

6 months

🌌🤖 Spectacular AI Adventure: "Milo & Ziggy: Embark on a Cosmic Journey" - A Heartwarming Tale of Friendship Beyond the Stars ✍️ Scenario: 100% Human Creativity 🖼️ Visuals: Crafted with 💖 / SDXL / ComfyUI 🎥 Production: @pika_labs 🎙️ Voices: @coqui_ai Curious about how we

13

31

163

Thibaud Zamora ∞

@thibaudz

2 years

Today, I launch the crowdfunding campaign for my Pir-AI-tes. 🎉 The very first artbook about Pirates with 100% of the artworks made with A.I. tools only. You can register for the launch on Kickstarter. Link in comment. Quote RT / RT VERY appreciated!

20

56

159

Thibaud Zamora ∞

@thibaudz

3 months

the new ipadapter by @cubiq are so great! thanks @peteromallet for the info!

5

25

162

Thibaud Zamora ∞

@thibaudz

2 months

StoryDiffusion seems very great and it's open-source (license unknown) can't wait to see how we can finetune and use it with other tools like IPAdapter & ComfyUI More example below👇

7

20

166

Thibaud Zamora ∞

@thibaudz

8 months

Wow. OAI just released the Dalle3 VAE and example of how to use it with Diffusers and SD 1.5! Great move! (link in the first comment)

11

27

163

Thibaud Zamora ∞

@thibaudz

2 years

✅Dreambooth running on windows ✅Lora running on windows ✅with SD 2.1 512 ✅and SD 5.1 768 v a kind of install is available on my github - (link in comments)

5

14

163

Thibaud Zamora ∞

@thibaudz

5 months

comparison of different "face technologies". You can download and play with the workflow (link in comment), many settings to test, combination of models, changing weights etc... more tests will be done when instant id will have a better integration. for now, my favorite is a

12

24

162

Thibaud Zamora ∞

@thibaudz

7 months

Pika 1.0 is incredible. This is from prompt only, first generation, no cherry-picking. But the poor dog gets a hat when sleeping, watch it in the thread. And choose what'll happen to it next!

8

16

164

Thibaud Zamora ∞

@thibaudz

2 months

some people asked me if i ll train controlnets for SD3. tldr ; i don't know. i trained all the main controlnets for SD2.1. for SDXL, i was in touch with stability (i give them my methodology, training scripts etc) ; in parallel, i trained and released OpenPose (i trained a few

19

9

163

Thibaud Zamora ∞

@thibaudz

1 year

BREAKING NEWS about ControlNet for #StableDiffusion 2.1 Thanks to @p1atdev_art , the safetensors version (pruned to 730mb) are now available!

7

22

162

Thibaud Zamora ∞

@thibaudz

1 year

Deepfloyd 🎉🎉🎉 Congrats @deepfloydai , @StabilityAI @EMostaque

GitHub - deep-floyd/IF

Contribute to deep-floyd/IF development by creating an account on GitHub.

github.com

7

23

161

Thibaud Zamora ∞

@thibaudz

7 months

i just updated the upscaler workflow. the new version fix the color washing issue. thanks for all people here and on discord who show me results with this node. (link below)

7

22

161

Thibaud Zamora ∞

@thibaudz

7 months

Let me introduce you to the (un)dress workflow. Now I have your attention. Thanks. I've been asked frequently about sharing my (re)dress workflow. While I understand the interest, I've decided not to disclose it due to obvious reasons... but for some people, reasons were not

30

18

159

Thibaud Zamora ∞

@thibaudz

6 months

new ai film done! we will release it in a few days.

10

3

156

Thibaud Zamora ∞

@thibaudz

2 years

One of The pirates' lairs #AiArt #ArtistOnTwitter #DigitalArt

7

12

149

Thibaud Zamora ∞

@thibaudz

6 months

ahah

8

16

154

Thibaud Zamora ∞

@thibaudz

7 months

AI is just one click.

18

16

154

Thibaud Zamora ∞

@thibaudz

2 years

You can be who you want - Harry Potter Edition! #stablediffusion #DeforumDiffusion #harrypotter

8

22

150

Thibaud Zamora ∞

@thibaudz

2 years

The cavern in the pirates' island #AiArt #ArtistOnTwitter #DigitalArt

8

15

140

Thibaud Zamora ∞

@thibaudz

5 months

it seems to be one of the missing part to get real AI actors. i think in 2024 we'll be able to: - generate our 3D character - having very good tools like this one for lipsync & emotions - get better emotions for AI voice then: - nice 3D environment generated with AI and with

12

28

150

Thibaud Zamora ∞

@thibaudz

7 months

LEGEND – wait for it – DARY A 360 turn in less 30 sec. StableZero123 + ComfyUI

11

19

139

Thibaud Zamora ∞

@thibaudz

4 months

. @runwayml 🫳🏻🎤

11

16

139

Thibaud Zamora ∞

@thibaudz

1 year

#ControlNet Openpose for #stablediffusion 2.X is released! ckpt: diffusers:

4

31

141

Thibaud Zamora ∞

@thibaudz

4 months

🚨 breaking hypothesis 🚨 facts: 1) sd3 use similar tech as sora 2) sora can make video and image conclusion: so if stability get more gpus, they may train stablevideo based on sd3 and achieved sora level. 🤯

14

9

141

Thibaud Zamora ∞

@thibaudz

1 year

Controlnet depth 2.1 is coming Still in training but here's a preview. It must be done tomorrow.

9

8

142

Thibaud Zamora ∞

@thibaudz

2 years

Light #deforum #DeforumDiffusion

3

16

138

Thibaud Zamora ∞

@thibaudz

9 months

Prediction: MidJourney will be integrated in X. Why? 1. The biggest clue is this screenshot (and it s not the first time, Elon talk about MJ) 2. Meta, Google and MSFT is adding generative AI in their platforms 3. MJ seems to lose user since the release of Dalle3, so they

36

10

140

Thibaud Zamora ∞

@thibaudz

6 months

new update🤯🤯🤯 next level and i have many others things to add to improve results

14

25

138

Thibaud Zamora ∞

@thibaudz

10 months

2023 seems really the year of AI Video! Deforum, Warp, Gen2, Pika and now that!

5

23

134

Thibaud Zamora ∞

@thibaudz

7 months

Discover ZipLoRA: a groundbreaking approach to generate any subject in any style, merging style, and subject LoRAs effectively. It offers high fidelity in both aspects. By Google Research one of the author is @natanielruizg , same as DreamBooth!⏬

6

24

136

Thibaud Zamora ∞

@thibaudz

5 months

rpgdiffusion seems incredible for prompt comprehension! see below (the most mindblowing example is the third for me)

6

11

136

Thibaud Zamora ∞

@thibaudz

7 months

Here's my tutorial to design your own "Pokémon" characters. (Using ComfyUI, IPAdapter, and SDXL Turbo). Try it and share your Chimeras!

3

26

133

Thibaud Zamora ∞

@thibaudz

1 year

Controlnet Color is now available for SD2.X As usual, the Emma Watson Prompt #stablediffusion #controlnet Links below

6

23

135

Thibaud Zamora ∞

@thibaudz

1 year

ControlNet - ZoeDepth is available for SD2.X Cooking is over, Muffins are ready! Imgs: 1) Original 2) ZoeDepth 3) DepthV1 You can use it with depth/le_res as preprocessor but it works better with ZoeDepth (My PR is not accepted yet but you can use my fork). links below

12

17

134

Thibaud Zamora ∞

@thibaudz

7 months

Quick movie (made in less than 15 minutes) to celebrate the access to @pika_labs new model All clips are done directly by text2video. Voice with @coqui_ai

14

18

132

Thibaud Zamora ∞

@thibaudz

2 years

I love #stablediffusion so many style available.

8

17

128

Thibaud Zamora ∞

@thibaudz

7 months

Ho ho ho! A free caption tool for Xmas! The more videos I create, the more I find myself in need of adding attractive captions. Unfortunately, I couldn't find a repository that made this process easy. Time constraints kept me from developing a tool myself. So, I decided to take

19

23

128

Thibaud Zamora ∞

@thibaudz

3 months

🫡🎊🚀

26

3

130

Thibaud Zamora ∞

@thibaudz

2 years

Just finished this piece... so GN! 🏴‍☠️💥 #AiArt #DigitalArt #ArtistOnTwitter

12

26

122

Thibaud Zamora ∞

@thibaudz

8 months

Watch my 2min. tutorial in which I explain step-by-step (and share!) my workflow using Motion to generate eye-catching 3D animations.

3

14

126

Thibaud Zamora ∞

@thibaudz

2 years

The treasure keeper #AiArt #ArtistOnTwitter

5

20

118

Thibaud Zamora ∞

@thibaudz

4 months

is people understand how this image is important? really. yes? no! more.

Emad

@EMostaque

4 months

“Photo of a red sphere on top of a blue cube. Behind them is a green triangle, on the right is a dog, on the left is a cat” #SD3

100

204

2K

16

6

120

Thibaud Zamora ∞

@thibaudz

6 months

who is porting photomaker for comfyui? 🙏

11

14

117

Thibaud Zamora ∞

@thibaudz

22 days

The key for SD3 seems to be : very long prompt (see the short version below... or don't, no you don't after all) An intimate, soulful portrait photograph of a majestic golden retriever, capturing the essence of this beloved canine breed known for their intelligence, loyalty, and

20

11

116

Thibaud Zamora ∞

@thibaudz

10 months

I just release the LoRA version of openpose controlnet XL. Available on the same repo: Results are a bit different than the full model but didn’t test enough to tell if it s better or worst.